© 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. 204216
    Prev
    Next
    INDEX
    Explanations

    answering questions

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

    hlsl assembly

    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
    io
    0.61
    IO
    0.56
    not
    0.55
    н
    0.51
    BL
    0.49
    :
    0.49
    eg
    0.48
    estructura
    0.48
    ṭ
    0.48
    ți
    0.48
    POSITIVE LOGITS
    饵
    0.64
    煊
    0.46
    वे
    0.46
     myocard
    0.45
    อร์ด
    0.45
     Dön
    0.44
     }}$
    0.44
    วม
    0.44
    产量
    0.44
    垮
    0.44
    Activations Density 0.000%

    No Known Activations