© 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. 169680
    Prev
    Next
    INDEX
    Explanations

    operated, limit, misleading, branded

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

    explains content following a reference

    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
    詛
    0.53
     लोकसभा
    0.52
     這個
    0.50
    tx
    0.48
    ǒ
    0.48
     ಆದರೆ
    0.48
    連接
    0.48
     Parmesan
    0.48
    νο
    0.47
    ㅂ
    0.47
    POSITIVE LOGITS
     that
    0.43
     unless
    0.43
     tuned
    0.41
     branded
    0.40
     الرس
    0.40
     bila
    0.39
     فرهنگ
    0.39
     icons
    0.38
     intricacies
    0.38
     themed
    0.38
    Activations Density 0.000%

    No Known Activations