© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    OpenAI, guidelines, NFT, website

    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
    {\'
    0.54
    \'{
    0.53
    established
    0.45
    apanicolaou
    0.45
     প্রকৃতপক্ষে
    0.44
    studentRecord
    0.44
    <unused2169>
    0.44
     popularly
    0.44
    frigerator
    0.44
    ೬
    0.44
    POSITIVE LOGITS
     و
    0.59
     condos
    0.59
     critters
    0.57
     نیست
    0.57
     לא
    0.56
     shenanigans
    0.55
     antics
    0.55
     regs
    0.54
     cosas
    0.54
     veracity
    0.54
    Activations Density 0.048%

    No Known Activations