Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109984
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric values with decimal points, particularly percentages or measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     mention
    -0.77
    PEAT
    -0.75
     möchten
    -0.73
     съ
    -0.71
     mwaka
    -0.69
    logne
    -0.68
    QueryBuilder
    -0.68
    풋
    -0.67
     touch
    -0.66
     سوق
    -0.66
    POSITIVE LOGITS
    licted
    0.75
    Detached
    0.74
    的区别
    0.72
    Cek
    0.72
    Ense
    0.71
     нау
    0.70
    Chapitre
    0.70
    tronics
    0.70
     Tuscan
    0.69
     kebun
    0.69
    Activations Density 0.059%

    No Known Activations