© 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. 10-GEMMASCOPE-RES-131K
    7. 74719
    Prev
    Next
    INDEX
    Explanations

    cats and what they do

    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_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
    *
    -3.22
     was
    -2.70
    抔
    -2.66
    也就是
    -2.56
    {
    -2.55
    0
    -2.36
    のは
    -2.23
    ay
    -2.23
    とその
    -2.23
    si
    -2.19
    POSITIVE LOGITS
    琑
    3.27
     inception
    2.69
    mpagne
    2.67
    秾
    2.59
    懨
    2.56
    ꜆
    2.55
    utterstock
    2.53
    幛
    2.36
    𐑂
    2.31
    OUTUBE
    2.30
    Activations Density 0.004%

    No Known Activations