© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8532
    Prev
    Next
    INDEX
    Explanations

    purpose and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yards
    1.03
    hava
    0.97
    ei
    0.89
    uatu
    0.86
    aña
    0.86
    cích
    0.86
    esian
    0.85
    h
    0.85
     flames
    0.85
    ené
    0.85
    POSITIVE LOGITS
     사항
    0.98
     редакти
    0.93
    б
    0.89
     essentielle
    0.84
    핳
    0.84
     funzionalità
    0.84
     punctu
    0.79
     reproducibility
    0.79
     staples
    0.79
     मसलन
    0.78
    Activations Density 0.475%

    No Known Activations