© 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. 111535
    Prev
    Next
    INDEX
    Explanations

    services and media

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

    list categorization

    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
    r
    0.55
    kę
    0.52
    k
    0.52
    ves
    0.51
    viving
    0.50
    j
    0.50
    ræ
    0.49
    rani
    0.48
    le
    0.48
    dwelling
    0.48
    POSITIVE LOGITS
    /////////////
    0.54
    ্যাস
    0.52
     создать
    0.50
    ణ
    0.49
     дата
    0.48
     supprimer
    0.47
    ٢
    0.47
    蹇
    0.46
     pstmt
    0.46
     DataType
    0.46
    Activations Density 0.000%

    No Known Activations