© 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. 7222
    Prev
    Next
    INDEX
    Explanations

    building in, been with

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

    long history

    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
     sentença
    0.53
    мере
    0.52
    מר
    0.52
    ски
    0.51
    לו
    0.50
    旿
    0.50
     assignee
    0.50
    веден
    0.50
    媜
    0.48
    گي
    0.47
    POSITIVE LOGITS
    ↵
    0.56
    >>
    0.52
    Ak
    0.52
    ac
    0.51
    =>
    0.49
    :<
    0.46
    Hin
    0.46
     Ukraj
    0.46
    Fe
    0.46
    HA
    0.45
    Activations Density 0.000%

    No Known Activations