© 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. 190221
    Prev
    Next
    INDEX
    Explanations

    arrival, purpose, visa, reef

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

    old testament and zhou

    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
    with
    0.70
    in
    0.57
    i
    0.54
    by
    0.51
    swith
    0.51
    open
    0.50
    under
    0.49
    암
    0.48
    only
    0.47
    or
    0.47
    POSITIVE LOGITS
     arrière
    0.52
     arrivée
    0.50
     intérêt
    0.47
     découvre
    0.47
     thở
    0.47
    ନ୍ତ
    0.47
     انرژی
    0.46
     œ
    0.46
    ﯿ
    0.46
    کٹ
    0.46
    Activations Density 0.000%

    No Known Activations