© 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. 225500
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    iann
    0.49
    velt
    0.47
    🏚
    0.46
     adsorb
    0.45
     Davenport
    0.44
    ranton
    0.44
     Shan
    0.43
     قلت
    0.43
     берегу
    0.43
    pict
    0.43
    POSITIVE LOGITS
    ל
    0.58
    ло
    0.51
    ل
    0.47
    加
    0.44
    л
    0.44
    लेट
    0.44
    ट
    0.44
    ע
    0.43
    ゼ
    0.43
    錐
    0.43
    Activations Density 0.001%

    No Known Activations