© 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. 168164
    Prev
    Next
    INDEX
    Explanations

    party in

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

    "Dear" followed by bracketed placeholders

    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
    JsonResponse
    0.45
    滘
    0.45
    Geschichte
    0.44
    華
    0.44
    くれました
    0.44
    網站
    0.43
     الزرا
    0.43
    專輯
    0.42
    雞
    0.42
     repurchase
    0.42
    POSITIVE LOGITS
    s
    0.56
    yn
    0.54
    yin
    0.51
    ln
    0.50
    llvm
    0.50
    IL
    0.49
    itan
    0.49
    yl
    0.49
    tan
    0.49
    tn
    0.48
    Activations Density 0.000%

    No Known Activations