© 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. 29810
    Prev
    Next
    INDEX
    Explanations

    SQL DECIMAL types

    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
    リオ
    0.41
     "&#
    0.37
     analysed
    0.37
     ');
    0.37
     presented
    0.36
    RefIn
    0.36
     ++;
    0.36
    presented
    0.35
     fomentar
    0.35
     আলোর
    0.35
    POSITIVE LOGITS
    める
    0.43
    ewa
    0.42
    कां
    0.40
    enbach
    0.40
     Watt
    0.40
    avut
    0.39
     ഉ
    0.38
    KON
    0.38
    滟
    0.38
    用水
    0.38
    Activations Density 0.001%

    No Known Activations