© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99158
    Prev
    Next
    INDEX
    Explanations

    effector in biological signaling

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

    biological terms related to effector molecules or cells in scientific contexts.

    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
    y
    -2.66
     хорошо
    -2.45
    te
    -2.25
    h
    -2.25
    t
    -2.19
    olusi
    -2.19
    ——”
    -2.17
    m
    -2.13
    秶
    -2.08
    …」
    -2.06
    POSITIVE LOGITS
    耵
    2.23
    0
    2.20
     of
    2.20
     
    2.20
     Which
    2.14
    नलोड
    2.11
    じゃなくて
    2.08
    replyreport
    2.06
    fotograf
    2.03
     publicación
    2.00
    Activations Density 0.008%

    No Known Activations