© 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. 194447
    Prev
    Next
    INDEX
    Explanations

    national sporting events

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

    dip each

    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
    樯
    0.47
    绦
    0.46
    દા
    0.45
     پاس
    0.45
     Batteries
    0.45
    鳎
    0.45
    äum
    0.44
     budynku
    0.44
     glaciers
    0.44
    喆
    0.44
    POSITIVE LOGITS
    dependent
    0.59
     salute
    0.46
    soever
    0.46
    Salah
    0.46
    ហារ
    0.45
    nx
    0.44
    mur
    0.44
    nable
    0.44
     engineered
    0.44
    Referensi
    0.44
    Activations Density 0.000%

    No Known Activations