© 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. 105103
    Prev
    Next
    INDEX
    Explanations

    cement tile, album version, deployment slot

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

    dictionary or object parameters

    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
    ys
    0.59
    els
    0.59
    ate
    0.55
     in
    0.53
    k
    0.53
    ons
    0.52
    eller
    0.52
    yl
    0.51
    ks
    0.50
    edge
    0.49
    POSITIVE LOGITS
    ﮈ
    0.64
    䣨
    0.54
     Kiến
    0.53
    뻥
    0.53
    дом
    0.52
     spécial
    0.52
     produisent
    0.52
     patrimoine
    0.50
    高志森
    0.50
    㙂
    0.50
    Activations Density 0.001%

    No Known Activations