© 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. 117667
    Prev
    Next
    INDEX
    Explanations

    cat and related words

    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
     Complications
    -0.82
     Chry
    -0.78
     Buys
    -0.77
     chaff
    -0.77
     CHECKBOX
    -0.76
    ucht
    -0.75
     coppia
    -0.74
    પ
    -0.74
     ponies
    -0.74
    jména
    -0.74
    POSITIVE LOGITS
     cat
    1.27
     Cat
    1.06
    cat
    1.02
    nip
    0.88
     personales
    0.86
    Cat
    0.85
     pada
    0.85
     unused
    0.84
     แม
    0.83
    tails
    0.82
    Activations Density 0.025%

    No Known Activations