© 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. 25683
    Prev
    Next
    INDEX
    Explanations

    .txt file extension

    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
    ↵
    -3.48
    (
    -2.83
    ↵↵
    -2.80
    {
    -2.77
        
    -2.63
    [
    -2.53
    <em>
    -2.50
    ”
    -2.34
      
    -2.31
    ,”
    -2.30
    POSITIVE LOGITS
    ᾔ
    2.34
    釭
    2.33
    ꔹ
    2.31
    derdag
    2.30
    럿
    2.28
    ли
    2.27
     แดง
    2.23
    ظمة
    2.20
    彡
    2.14
    ᠂
    2.14
    Activations Density 0.009%

    No Known Activations