© 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. 12367
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation

    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
     (
    -1.05
     to
    -1.03
    ̴
    -1.03
    mutate
    -1.03
     in
    -1.03
    
    -0.97
    skjaer
    -0.94
     information
    -0.91
    StringField
    -0.91
    cazione
    -0.89
    POSITIVE LOGITS
    reur
    1.13
    ︓
    1.08
    Langkah
    1.07
    Pgina
    1.06
    Penjelasan
    1.05
    Keterangan
    1.05
    Lịch
    1.05
    ㄟ
    1.05
    Estos
    1.05
    時間は
    1.05
    Activations Density 0.005%

    No Known Activations