© 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. 36103
    Prev
    Next
    INDEX
    Explanations

    lists of words

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

    technical terms and concepts

    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
    op
    0.48
    ве
    0.47
    торой
    0.45
    ق
    0.45
     sulphur
    0.45
    yn
    0.44
    ین
    0.44
    and
    0.44
    ח
    0.44
    angs
    0.43
    POSITIVE LOGITS
     എന്ന്
    0.54
    এটা
    0.53
     ഇത്
    0.52
    ının
    0.51
     rendelkez
    0.50
     нравится
    0.49
     erfüllen
    0.49
     Schreiben
    0.49
     artt
    0.48
     എടു
    0.48
    Activations Density 0.000%

    No Known Activations