© 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. 187458
    Prev
    Next
    INDEX
    Explanations

    specific per

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

    Art direction, construction, writing

    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
     posing
    0.47
    ड़ियों
    0.47
     Garth
    0.47
     Montague
    0.46
     Pius
    0.45
     اینڈ
    0.45
    絟
    0.45
     Galveston
    0.45
     MHK
    0.44
     bibliographic
    0.44
    POSITIVE LOGITS
     সা
    0.49
    FI
    0.48
    ":[],
    0.46
     ভা
    0.44
    éal
    0.44
    unge
    0.43
    ’
    0.43
    Ó
    0.43
     realizada
    0.42
     线
    0.42
    Activations Density 0.000%

    No Known Activations