© 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. 110634
    Prev
    Next
    INDEX
    Explanations

    full content descriptors

    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
     closed
    -0.80
     einander
    -0.76
     dét
    -0.76
    全家
    -0.73
    お値段
    -0.72
     fully
    -0.71
     pleinement
    -0.70
     Closed
    -0.69
     pone
    -0.69
    ffl
    -0.69
    POSITIVE LOGITS
     Italians
    0.83
    گر
    0.82
     Spaniards
    0.81
     asupra
    0.79
    size
    0.79
     article
    0.79
    饞
    0.78
     мнению
    0.77
     aici
    0.77
    Ą
    0.77
    Activations Density 0.031%

    No Known Activations