© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73332
    Prev
    Next
    INDEX
    Explanations

    distinguishing types or diagnoses

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or specialized terminology in academic and scientific writing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on specialized technical and clinical terms (and other formal, content-bearing words) found in medical and scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nguoi
    -0.84
     élas
    -0.81
     notation
    -0.81
    бку
    -0.80
    ciaal
    -0.79
     want
    -0.79
     GIRLS
    -0.79
    ographies
    -0.78
    nsylvania
    -0.78
    Amt
    -0.78
    POSITIVE LOGITS
     identification
    1.45
     distinguishing
    1.44
     identifying
    1.37
     distinctive
    1.34
     identity
    1.24
     distinguishable
    1.21
     identify
    1.20
     clues
    1.19
     distinguish
    1.16
     discriminating
    1.15
    Activations Density 0.204%

    No Known Activations