© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11351
    Prev
    Next
    INDEX
    Explanations

    Image taken, delayed treatment

    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
     JLabel
    -1.04
    炕
    -1.00
     legt
    -0.96
     kreat
    -0.95
    ПЕ
    -0.95
    pawn
    -0.93
    泵
    -0.92
     WiFi
    -0.91
    КЕ
    -0.91
    xvii
    -0.91
    POSITIVE LOGITS
     as
    1.05
    改變
    0.94
     some
    0.90
     there
    0.88
    簡單
    0.87
     when
    0.86
    最后一个
    0.86
    .......
    0.86
    俨
    0.85
    There
    0.84
    Activations Density 0.009%

    No Known Activations