© 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. 10-GEMMASCOPE-RES-131K
    7. 15050
    Prev
    Next
    INDEX
    Explanations

    cells, bodies, logy

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

    names of biological structures, organisms, or anatomical parts.

    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_10/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
     helg
    -1.35
     when
    -1.24
     of
    -1.23
     pisang
    -1.20
    ditionally
    -1.20
     what
    -1.20
    無法
    -1.15
     alip
    -1.14
     Januari
    -1.14
    what
    -1.14
    POSITIVE LOGITS
     októ
    1.48
    idopsis
    1.42
     jabón
    1.41
     největ
    1.40
    CHREIB
    1.38
    mamış
    1.38
     algunas
    1.37
     sorprend
    1.35
     arries
    1.34
     иногда
    1.34
    Activations Density 0.321%

    No Known Activations