© 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. 11323
    Prev
    Next
    INDEX
    Explanations

    codes and programming concepts

    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
     éléments
    -1.08
     菇
    -1.07
     Clientes
    -1.06
    understood
    -1.04
     papiers
    -1.01
    Organisator
    -1.01
     historien
    -0.99
     ロゴ
    -0.98
    μάτων
    -0.97
    ㍑
    -0.96
    POSITIVE LOGITS
     from
    1.10
     to
    1.07
     when
    1.01
     since
    0.98
     mengingat
    0.98
     beantworten
    0.98
    数十
    0.94
     When
    0.92
    ACKNOWLEDGMENT
    0.91
     using
    0.91
    Activations Density 0.004%

    No Known Activations