© 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. 115992
    Prev
    Next
    INDEX
    Explanations

    feather necklace

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

    effectively realize

    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
     LAY
    0.49
     CITY
    0.48
    URA
    0.47
    チ
    0.46
    랜
    0.46
    Ti
    0.44
     naš
    0.44
     スポーツ
    0.44
    لمات
    0.44
    Ö
    0.43
    POSITIVE LOGITS
    泞
    0.53
    ichage
    0.44
    合法
    0.44
    馅
    0.44
    အောင်
    0.44
    违
    0.44
    构成
    0.43
    哼
    0.43
    日志
    0.43
    ordinary
    0.42
    Activations Density 0.000%

    No Known Activations