© 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. 19961
    Prev
    Next
    INDEX
    Explanations

    kind, K words

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

    k, Kind, kinky, K-means, k-NN, Kivy, kb

    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
    hz
    0.77
     निशाना
    0.77
    h
    0.77
    ൂ
    0.73
    ا
    0.72
    。</
    0.71
     imasmim
    0.70
    busca
    0.70
    یا
    0.70
    ്ര
    0.70
    POSITIVE LOGITS
     on
    1.09
    .
    1.05
     to
    0.99
    8
    0.93
    9
    0.91
     in
    0.89
    ,
    0.86
     by
    0.82
    1
    0.82
    ]
    0.81
    Activations Density 0.254%

    No Known Activations