© 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. 109821
    Prev
    Next
    INDEX
    Explanations

    start of specific phrases

    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
    ęcz
    -0.79
     so
    -0.77
    يده
    -0.74
    覚悟
    -0.73
     into
    -0.73
     similar
    -0.73
    thritis
    -0.73
     gala
    -0.72
     even
    -0.71
    譬
    -0.71
    POSITIVE LOGITS
    Anderson
    1.17
     Anderson
    1.11
     anglès
    0.97
     ANDERSON
    0.96
    אָ
    0.93
    想要
    0.92
    🏉
    0.91
    issement
    0.83
    imą
    0.83
    żeń
    0.82
    Activations Density 0.003%

    No Known Activations