© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5589
    Prev
    Next
    INDEX
    Explanations

    Vendor, question, mother, specific

    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
    "));
    0.45
     PUBLIC
    0.44
    GINIA
    0.44
     index
    0.44
    gic
    0.43
    oll
    0.43
     Coalition
    0.43
    public
    0.43
    vall
    0.43
     understand
    0.42
    POSITIVE LOGITS
    ጢ
    0.49
     sagging
    0.48
     Mavic
    0.48
    一声
    0.47
     pensamientos
    0.47
     корпуса
    0.47
     sempat
    0.46
    خی
    0.46
    個性
    0.45
    今年は
    0.45
    Activations Density 0.000%

    No Known Activations