© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37521
    Prev
    Next
    INDEX
    Explanations

    Vintage Oak, close friend

    np_acts-logits-general · gemini-2.5-flash-lite

    fluctuatesLeadingTranslatefilled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    湆
    0.51
    氵
    0.49
    ocont
    0.46
    优秀
    0.46
    奴
    0.46
    绀
    0.45
    וס
    0.45
    迦
    0.45
    ัป
    0.45
    喑
    0.44
    POSITIVE LOGITS
     خوش
    0.49
    pline
    0.46
    cheek
    0.46
    marriage
    0.45
    vine
    0.44
    development
    0.43
     عزی
    0.43
    valu
    0.42
    computation
    0.41
    scrape
    0.41
    Activations Density 0.000%

    No Known Activations