© 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. 105796
    Prev
    Next
    INDEX
    Explanations

    US administration

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

    help with

    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
    ai
    0.64
    на
    0.57
    au
    0.57
    aini
    0.57
    ag
    0.55
    air
    0.54
    aw
    0.53
    u
    0.53
    uhe
    0.52
    mpl
    0.51
    POSITIVE LOGITS
    ESSITY
    0.47
    стіше
    0.45
    Synopsis
    0.45
    妧
    0.44
     অভাব
    0.43
    ト
    0.43
    概述
    0.43
     horrors
    0.42
    ドド
    0.42
    ᅬ
    0.42
    Activations Density 0.001%

    No Known Activations