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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11490
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
    gridColumn
    -1.84
    ૉ
    -1.69
    әм
    -1.54
    领先
    -1.47
    いつもの
    -1.45
     fiecare
    -1.41
    Aktual
    -1.41
    Reklama
    -1.40
    ＊＊＊
    -1.38
    この日
    -1.38
    POSITIVE LOGITS
    oczes
    1.61
     after
    1.61
     of
    1.55
    fordshire
    1.51
    ̣
    1.44
     daring
    1.41
     African
    1.37
    暧
    1.34
    学生的
    1.34
     senere
    1.34
    Activations Density 0.074%

    No Known Activations