© 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. 246083
    Prev
    Next
    INDEX
    Explanations

    in or of

    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
    罗马
    0.49
    خانه
    0.49
     Поль
    0.46
    加热
    0.46
     personalidad
    0.45
    பிற
    0.44
    性格
    0.44
    傈
    0.43
    تبار
    0.42
    家族
    0.41
    POSITIVE LOGITS
    ya
    0.58
    omb
    0.49
     fortsatt
    0.49
     đu
    0.47
     अजून
    0.45
    apak
    0.44
    osh
    0.44
    .}}
    0.44
    fr
    0.43
     phòng
    0.43
    Activations Density 0.001%

    No Known Activations