© 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. 990
    Prev
    Next
    INDEX
    Explanations

    labels and states

    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
    ূর্ত
    0.38
    ভৃতি
    0.38
    esinin
    0.37
    াস্থ্যের
    0.37
    锄
    0.37
    orphisms
    0.37
     자체가
    0.37
    পালের
    0.36
    기도
    0.36
    たちが
    0.36
    POSITIVE LOGITS
    /
    0.59
     |
    0.54
     or
    0.46
     /
    0.46
    ;
    0.46
     (-)
    0.46
    .
    0.44
    ',
    0.44
     (
    0.43
     (+
    0.43
    Activations Density 0.081%

    No Known Activations