© 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. 107789
    Prev
    Next
    INDEX
    Explanations

    facilities in

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

    legal or factual charges

    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
    良好的
    0.45
     Україні
    0.44
    洗
    0.44
    .。
    0.44
    地面
    0.43
    OfType
    0.43
    떄
    0.43
    xFF
    0.42
    食用
    0.42
    ب
    0.41
    POSITIVE LOGITS
    gripper
    0.49
     destacó
    0.49
     मालिके
    0.48
     jai
    0.48
    খিক
    0.48
     মাদ্র
    0.47
    jail
    0.46
    anız
    0.46
    detach
    0.45
    gca
    0.45
    Activations Density 0.001%

    No Known Activations