© 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. 17511
    Prev
    Next
    INDEX
    Explanations

    licenses and protocol

    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
    olisme
    0.43
    회가
    0.42
    壶
    0.41
    회를
    0.39
    uity
    0.39
    觴
    0.38
     THAT
    0.38
    羢
    0.37
    ヤモンド
    0.37
    DIALOG
    0.37
    POSITIVE LOGITS
     mom
    0.38
    timezone
    0.38
    ha
    0.37
     abstract
    0.37
    rául
    0.37
     reasonably
    0.36
    tama
    0.36
    dad
    0.36
     dili
    0.36
     defer
    0.35
    Activations Density 0.000%

    No Known Activations