© 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. 246156
    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
    iyu
    0.50
    _->
    0.48
    bdb
    0.47
    pera
    0.46
     dyd
    0.46
    loj
    0.46
     सश
    0.46
     ]];
    0.45
    parser
    0.44
     ステン
    0.44
    POSITIVE LOGITS
    刊
    0.48
    НГ
    0.48
    ка
    0.44
    ुन
    0.44
    ве
    0.44
     impianti
    0.44
    ко
    0.44
    ک
    0.43
    цу
    0.43
     тек
    0.43
    Activations Density 0.000%

    No Known Activations