© 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. 114394
    Prev
    Next
    INDEX
    Explanations

    shopping destination

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

    those reset

    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
     ângulo
    0.49
    點
    0.48
     pâle
    0.46
    說明
    0.46
    說
    0.46
    틴
    0.46
    니
    0.45
    ang
    0.44
    ט
    0.44
    翻译
    0.44
    POSITIVE LOGITS
     परिस्थित
    0.49
     Mandel
    0.48
     possui
    0.47
     devotion
    0.44
    retail
    0.43
     Afghan
    0.43
     மரிய
    0.42
     sizeable
    0.42
     افغانستان
    0.42
     deewana
    0.42
    Activations Density 0.001%

    No Known Activations