© 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. 118731
    Prev
    Next
    INDEX
    Explanations

    slow and fast animals

    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
     ráp
    -0.71
    🗒
    -0.68
    ௰
    -0.68
     gn
    -0.66
     proteína
    -0.66
    関連項目
    -0.66
    منع
    -0.66
     lysine
    -0.65
    jetty
    -0.65
    eyed
    -0.65
    POSITIVE LOGITS
     tortoise
    2.13
    slow
    1.93
     slow
    1.92
    Slow
    1.77
     Slow
    1.73
     Tortoise
    1.72
     hare
    1.57
    fast
    1.57
     turtle
    1.55
     快
    1.52
    Activations Density 0.014%

    No Known Activations