© 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. 203877
    Prev
    Next
    INDEX
    Explanations

    got a

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

    identifying explanations or descriptions

    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
    Дан
    0.56
    בק
    0.55
    孛
    0.53
    Beim
    0.51
     experimentar
    0.50
    АН
    0.50
    дан
    0.49
    سری
    0.48
    Ꮔ
    0.48
     Дан
    0.48
    POSITIVE LOGITS
    ly
    0.54
    uge
    0.51
    og
    0.50
    erv
    0.49
     زين
    0.48
    io
    0.47
    re
    0.46
    uhu
    0.46
    lodge
    0.45
    un
    0.45
    Activations Density 0.001%

    No Known Activations