© 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. 34-GEMMASCOPE-RES-131K
    7. 109854
    Prev
    Next
    INDEX
    Explanations

    group member

    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_34/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
    שׁ
    -0.79
    Среди
    -0.77
     wel
    -0.76
     blues
    -0.75
     blan
    -0.75
     pian
    -0.73
     lighten
    -0.72
     reversed
    -0.72
    斯特
    -0.70
    琴
    -0.69
    POSITIVE LOGITS
     member
    1.44
    成员
    1.25
     members
    1.23
    メンバー
    1.23
    group
    1.23
     group
    1.22
     MEMBER
    1.19
    成員
    1.17
     Member
    1.13
    Members
    1.13
    Activations Density 0.038%

    No Known Activations