© 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. 124076
    Prev
    Next
    INDEX
    Explanations

    someone else

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

    generic.default, max, meta

    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
     прибыли
    0.57
     منح
    0.49
     الرجل
    0.49
     மிகப்பெரிய
    0.49
     جدید
    0.46
     채
    0.46
     પ
    0.45
     नवीन
    0.45
     ಮತ್ತು
    0.45
     incroy
    0.45
    POSITIVE LOGITS
    ྀ
    0.52
     do
    0.46
    леге
    0.46
    IE
    0.45
     prove
    0.44
     kg
    0.43
     su
    0.42
    есть
    0.42
    ﾚ
    0.42
    eq
    0.42
    Activations Density 0.000%

    No Known Activations