© 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. 22-GEMMASCOPE-RES-131K
    7. 11548
    Prev
    Next
    INDEX
    Explanations

    not a... but a

    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_22/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
    capulco
    -0.96
    postolic
    -0.90
     assist
    -0.90
     gdzie
    -0.88
     których
    -0.87
    embang
    -0.85
    vádz
    -0.85
     szt
    -0.84
     dichos
    -0.84
     via
    -0.84
    POSITIVE LOGITS
     is
    1.15
    ただの
    1.12
    เป็น
    1.07
     it
    0.99
    จะเป็น
    0.96
     явля
    0.96
    眉毛
    0.94
    MessageOf
    0.93
    become
    0.93
     isang
    0.92
    Activations Density 0.104%

    No Known Activations