© 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. 109826
    Prev
    Next
    INDEX
    Explanations

    Pakistani government and institutions

    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
    chiato
    -0.93
    酊
    -0.87
    ppelin
    -0.84
    tagonal
    -0.83
    endola
    -0.82
    ЦИИ
    -0.81
    )"),
    -0.78
    CLIP
    -0.78
     姜
    -0.78
    คลิ
    -0.77
    POSITIVE LOGITS
     summary
    0.87
     provinces
    0.79
     Opfer
    0.73
     Privat
    0.71
     summarised
    0.69
     provincial
    0.66
    讲
    0.66
    灘
    0.65
     references
    0.64
    滩
    0.64
    Activations Density 0.011%

    No Known Activations