© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66303
    Prev
    Next
    INDEX
    Explanations

    Ia supernova, tooth enamel, core analysis, APP

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

    scientific data points and measurements from research papers and technical documents.

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

    The neuron is sensitive to numeric measurements and quantitative data (i.e. tokens representing numbers or measurement values).

    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
     cadastro
    -0.98
     delegación
    -0.91
    ﺅ
    -0.91
    falt
    -0.90
     agencia
    -0.88
    Aph
    -0.88
    Rankings
    -0.87
     Inten
    -0.85
    Intended
    -0.85
    етесь
    -0.85
    POSITIVE LOGITS
    infect
    0.88
     reliable
    0.88
     זיך
    0.86
     மற்றும்
    0.84
     These
    0.84
    响起
    0.83
    dlc
    0.82
     питання
    0.82
    Toluene
    0.81
     indicating
    0.81
    Activations Density 0.141%

    No Known Activations