© 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. 65348
    Prev
    Next
    INDEX
    Explanations

    medical/technical terms followed by punctuation

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

    The neuron recognizes details in scientific or technical texts, particularly focusing on numerical values, measurements, and technical specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     τὸν
    -1.41
    ଶ
    -1.24
    ologische
    -1.20
     parteci
    -1.20
     maail
    -1.16
    ffilm
    -1.15
    When
    -1.14
     člověk
    -1.13
    Ведь
    -1.11
    Often
    -1.10
    POSITIVE LOGITS
     with
    1.31
     max
    1.20
     ausreichend
    1.15
     prefer
    1.15
     usando
    1.14
     standard
    1.12
     pensando
    1.12
     all
    1.12
     используются
    1.09
     commencer
    1.09
    Activations Density 0.107%

    No Known Activations