© 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. 193393
    Prev
    Next
    INDEX
    Explanations

    Florida, bedroom, black, family, business

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

    and or

    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
    USES
    0.47
    誦
    0.47
    競馬
    0.45
    杢
    0.45
     ойной
    0.44
    蓯
    0.44
    랫
    0.44
     بیٹنگ
    0.43
    することを
    0.42
    カウン
    0.42
    POSITIVE LOGITS
     حالة
    0.46
    nje
    0.46
     zumindest
    0.45
     toolbox
    0.45
     sakura
    0.45
     pression
    0.44
     gore
    0.43
     pust
    0.43
    }]{
    0.42
     brill
    0.42
    Activations Density 0.002%

    No Known Activations