© 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. 156628
    Prev
    Next
    INDEX
    Explanations

    corn, survivor, eruption, game, necessary

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

    names, boxes, or instability

    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
    لب
    0.47
    الم
    0.46
    نوان
    0.45
     સારું
    0.44
    堝
    0.44
    الب
    0.43
    価値
    0.43
     تجارت
    0.43
    ൽ
    0.43
    لیکن
    0.42
    POSITIVE LOGITS
     inquis
    0.49
     (.)
    0.46
     backpack
    0.44
    теля
    0.44
     кажу
    0.44
     кален
    0.43
     пока
    0.42
     attest
    0.42
     repress
    0.42
     раскры
    0.42
    Activations Density 0.000%

    No Known Activations