© 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. 136089
    Prev
    Next
    INDEX
    Explanations

    Harry Winston skin prior

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

    assessment and bias

    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
    ‹
    0.48
    simulate
    0.44
    ジュン
    0.44
    lesson
    0.43
    也可以
    0.43
    Adapted
    0.43
    texttt
    0.42
    课堂
    0.42
    —
    0.41
    Audio
    0.41
    POSITIVE LOGITS
     beslut
    0.57
     malls
    0.54
     vij
    0.50
     divor
    0.49
     shortfall
    0.49
     SQL
    0.47
     Kyrgyzstan
    0.47
     WOM
    0.47
     überprü
    0.47
    ብስ
    0.47
    Activations Density 0.000%

    No Known Activations