© 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. 190756
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or qualifiers

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

    classicbeastdatasetsBladeopusdot

    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
    pipe
    0.52
     pipe
    0.50
    diary
    0.47
     Zusammenhang
    0.46
     管
    0.46
    piper
    0.45
    elevator
    0.45
    dal
    0.45
    arc
    0.45
     कॉरिडोर
    0.45
    POSITIVE LOGITS
    ⚖
    0.50
    ва
    0.49
    ление
    0.47
    嘩
    0.46
     чыныгы
    0.46
    времен
    0.46
    ЛИ
    0.45
    дж
    0.45
    మీ
    0.45
    мену
    0.45
    Activations Density 0.000%

    No Known Activations