© 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. 34-GEMMASCOPE-RES-131K
    7. 99809
    Prev
    Next
    INDEX
    Explanations

    shark bites and biting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     chickens
    -0.79
    шот
    -0.77
     interstate
    -0.76
    rishnan
    -0.74
    entrySet
    -0.74
     Cardiac
    -0.74
    burned
    -0.74
    topes
    -0.73
     vingt
    -0.72
    queiro
    -0.71
    POSITIVE LOGITS
     bite
    3.95
     bites
    3.47
     biting
    3.19
    Bite
    3.06
    bite
    3.05
     Bite
    3.00
     Bites
    2.59
     bitten
    2.47
    bites
    2.42
     teeth
    2.41
    Activations Density 0.033%

    No Known Activations