© 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. 34-GEMMASCOPE-RES-131K
    7. 57311
    Prev
    Next
    INDEX
    Explanations

    C57BL/6 mice

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

    mouse strain names like C57BL/6, BALB/c in scientific literature.

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

    This neuron detects mentions of specific laboratory mouse strain identifiers (alphanumeric codes like “C57BL/6,” “DBA/1,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    のよう
    -0.80
    ssy
    -0.71
    grandfather
    -0.69
     Tomáš
    -0.69
     wam
    -0.69
    驱
    -0.69
    ⽣
    -0.69
     procurement
    -0.68
    пке
    -0.66
    rator
    -0.66
    POSITIVE LOGITS
     became
    0.75
    認定
    0.73
    chito
    0.72
     Laurel
    0.66
    bul
    0.66
     vět
    0.66
    signol
    0.66
    rosz
    0.65
    Bul
    0.65
    民眾
    0.65
    Activations Density 0.092%

    No Known Activations