© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 223365
    Prev
    Next
    INDEX
    Explanations

    irregular arrays designed for Disk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    DOUBLE
    0.44
    ኡ
    0.44
     カーボン
    0.43
    കൻ
    0.42
     Put
    0.41
     Profession
    0.41
     حک
    0.41
    డ్‌
    0.41
    癬
    0.41
     engage
    0.40
    POSITIVE LOGITS
    ornos
    0.52
     geophysical
    0.38
    emura
    0.38
     debtors
    0.37
    elia
    0.37
     exports
    0.37
    antil
    0.36
     barrels
    0.36
    نتي
    0.36
     Eater
    0.36
    Activations Density 0.000%

    No Known Activations