© 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. 156030
    Prev
    Next
    INDEX
    Explanations

    names, actions, and objects

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

    communication and specialized knowledge

    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
     молодо
    0.46
    дви
    0.45
    _.
    0.45
    э
    0.44
    SuspendLayout
    0.44
    ПО
    0.43
     LID
    0.42
    ,
    0.42
     uploads
    0.42
     Technology
    0.42
    POSITIVE LOGITS
    کرات
    0.52
    欢乐
    0.49
    atoms
    0.48
     theologians
    0.48
     orphans
    0.47
     ഒഴി
    0.47
    jeron
    0.46
    냐면
    0.45
     nást
    0.45
    龛
    0.45
    Activations Density 0.001%

    No Known Activations