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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8667
    Prev
    Next
    INDEX
    Explanations

    physicochemical effect

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

    scientific or technical terms and effects in academic or technical documents.

    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
     improvisation
    -0.88
    Registro
    -0.81
    zmán
    -0.79
    dotta
    -0.77
     smugglers
    -0.71
    lemented
    -0.71
    Ruta
    -0.71
    椁
    -0.70
    Infection
    -0.70
    rael
    -0.70
    POSITIVE LOGITS
     effect
    3.53
     Effect
    2.63
    effect
    2.61
     efecto
    2.34
    Effect
    2.31
     effects
    2.31
    效应
    2.14
     эффек
    2.11
     эффект
    2.05
     effetto
    1.95
    Activations Density 0.136%

    No Known Activations