© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125270
    Prev
    Next
    INDEX
    Explanations

    channels, reefs, banana, centuries

    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_31_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
    JECTION
    0.57
    ว้
    0.51
    pmod
    0.49
    ورد
    0.47
    면
    0.47
    рио
    0.47
    ጥረ
    0.45
    ็ค
    0.45
    ώσεις
    0.43
    א
    0.43
    POSITIVE LOGITS
    ckel
    0.53
     KPIs
    0.50
     Gazprom
    0.48
     dữ
    0.48
     GeV
    0.48
     RNAs
    0.47
     GPUs
    0.47
    thias
    0.47
     oper
    0.46
     dimethyl
    0.46
    Activations Density 0.000%

    No Known Activations