© 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. 110498
    Prev
    Next
    INDEX
    Explanations

    official document language

    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
    via
    -0.70
    Others
    -0.70
     уника
    -0.69
    قامة
    -0.69
     Virtual
    -0.69
    登录
    -0.68
     volantes
    -0.65
     малко
    -0.64
     Others
    -0.64
    にある
    -0.64
    POSITIVE LOGITS
     Friends
    0.86
    ynos
    0.83
    Friends
    0.80
    HAUS
    0.79
    igare
    0.77
    äge
    0.76
    ◑
    0.73
     bread
    0.73
     orche
    0.73
     discos
    0.72
    Activations Density 0.012%

    No Known Activations