© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54194
    Prev
    Next
    INDEX
    Explanations

    codes, licenses, and interventions

    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
    無し
    -1.07
     mitään
    -1.06
    の為
    -1.03
    ToServer
    -1.02
     улы
    -1.02
    ほら
    -1.02
    為に
    -1.02
    Siehe
    -1.00
    のですか
    -1.00
    arranty
    -0.96
    POSITIVE LOGITS
    がありますが
    1.39
    もありますが
    1.34
    があるので
    1.20
    は
    1.09
    などの
    1.08
    Gön
    1.08
     is
    1.03
    🛏
    1.01
    <bos>
    1.00
    ametric
    0.99
    Activations Density 0.000%

    No Known Activations