© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109805
    Prev
    Next
    INDEX
    Explanations

    fighting ring

    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
     presidency
    -0.90
     Иванович
    -0.80
    Vezi
    -0.77
     søndag
    -0.77
    ghalaya
    -0.75
    ectoria
    -0.75
    NPP
    -0.75
     СПб
    -0.72
     Reino
    -0.71
    obec
    -0.71
    POSITIVE LOGITS
     ropes
    3.03
     rope
    2.02
     Rope
    1.55
    Rope
    1.46
     canvas
    1.43
     apron
    1.20
     cuerdas
    1.18
    canvas
    1.17
    rope
    1.14
    ロープ
    1.13
    Activations Density 0.037%

    No Known Activations