© 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. 109712
    Prev
    Next
    INDEX
    Explanations

    code comments and special characters

    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
    ubat
    -0.71
    micros
    -0.70
     ਵ
    -0.70
    prefixes
    -0.68
    ígeno
    -0.68
    鳅
    -0.67
     STANDARDS
    -0.67
     thermally
    -0.67
    ujan
    -0.66
    ylinder
    -0.65
    POSITIVE LOGITS
    彌
    0.73
    りん
    0.73
    ළ
    0.70
    ereg
    0.67
    ͩ
    0.63
    anskrit
    0.63
    护
    0.63
     جديد
    0.62
     boca
    0.61
     veterinary
    0.61
    Activations Density 0.044%

    No Known Activations