© 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. 73839
    Prev
    Next
    INDEX
    Explanations

    languages, foreign words, shapes, numbers

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

    celebrities, coworker, money, Bartholomew

    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
    緯
    0.47
    rapport
    0.45
    勁
    0.45
    嬿
    0.44
    を感じ
    0.44
     দেহে
    0.42
     シン
    0.42
    هار
    0.42
    コル
    0.41
    最
    0.41
    POSITIVE LOGITS
    otle
    0.53
    étant
    0.52
    ova
    0.47
     tamaños
    0.45
     추출
    0.44
    사각형
    0.44
    ikar
    0.44
    inko
    0.44
    iller
    0.44
     जूते
    0.44
    Activations Density 0.000%

    No Known Activations