© 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. 138
    Prev
    Next
    INDEX
    Explanations

    URLs after keywords

    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
     convective
    0.37
    SANIT
    0.37
    قطه
    0.36
    াহরণ
    0.35
     connotations
    0.35
     mucous
    0.35
    اونلو
    0.34
    䊂
    0.34
     సన్నివేశ
    0.34
    arrêté
    0.34
    POSITIVE LOGITS
    /
    0.94
    /?
    0.65
    /[
    0.63
    /%
    0.61
    /)
    0.60
    /(
    0.59
    /{
    0.59
    /.
    0.57
    /${
    0.55
    /,
    0.55
    Activations Density 0.039%

    No Known Activations