© 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. 22-GEMMASCOPE-RES-131K
    7. 25782
    Prev
    Next
    INDEX
    Explanations

    import statements

    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_22/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
     somewhere
    -1.20
     poème
    -1.16
    Če
    -1.15
    Более
    -1.13
     {
    -1.11
     dessutom
    -1.10
    Bürger
    -1.06
     sebaik
    -1.06
    єра
    -1.06
     kekinian
    -1.04
    POSITIVE LOGITS
     and
    1.42
    <em>
    1.20
    <strong>
    1.20
    Z
    1.07
    el
    1.05
    ische
    0.99
    J
    0.96
    B
    0.95
    "
    0.91
    ica
    0.91
    Activations Density 0.016%

    No Known Activations