© 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. 121936
    Prev
    Next
    INDEX
    Explanations

    home for, afford meat, line does

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

    lists of examples

    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
     Affairs
    0.44
    까요
    0.44
     하고
    0.43
     incline
    0.42
     high
    0.42
     MUL
    0.41
    식을
    0.40
    {\$
    0.40
     khỏi
    0.40
    {[
    0.39
    POSITIVE LOGITS
    pageToken
    0.50
    les
    0.48
     スペ
    0.48
     वर्ड
    0.48
     રૂપ
    0.47
    ta
    0.46
     Nuestros
    0.45
    liegen
    0.45
     vacanam
    0.45
     १९
    0.44
    Activations Density 0.000%

    No Known Activations