© 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. 11097
    Prev
    Next
    INDEX
    Explanations

    over the last

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

    over the Internet

    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
    speople
    0.39
     прой
    0.38
     dure
    0.38
    েকে
    0.37
    秦
    0.37
    قي
    0.36
     conseguido
    0.36
     ダーク
    0.36
    ớt
    0.35
    நாதன்
    0.35
    POSITIVE LOGITS
    이지만
    0.44
    但在
    0.42
     н
    0.41
     ندارد
    0.40
     však
    0.39
    랗
    0.39
    جہاں
    0.39
     نیست
    0.38
     ně
    0.38
     nodos
    0.38
    Activations Density 0.000%

    No Known Activations