© 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. 9966
    Prev
    Next
    INDEX
    Explanations

    of the following

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

    weights, randomly, blocks, run

    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
    но
    0.55
    Khi
    0.54
    И
    0.52
    될
    0.52
    Ла
    0.52
    Стро
    0.52
    멤버
    0.50
    خی
    0.50
    ЛИ
    0.50
    키
    0.50
    POSITIVE LOGITS
     happening
    0.54
     Netflix
    0.46
     Affinity
    0.44
     Happens
    0.44
     TripAdvisor
    0.44
     Physically
    0.44
     happ
    0.43
    aths
    0.42
     BJP
    0.42
     stocking
    0.42
    Activations Density 0.000%

    No Known Activations