© 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. 47020
    Prev
    Next
    INDEX
    Explanations

    delivery marks

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

    "not" an ethical issue

    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
     mixts
    0.51
    ಲ
    0.51
    サイト
    0.49
     вашу
    0.47
    離婚
    0.46
    ジタル
    0.45
     Kurds
    0.44
     ഖ
    0.44
    你們
    0.44
    íss
    0.44
    POSITIVE LOGITS
     frustrate
    0.54
     frustration
    0.52
     an
    0.49
    元件
    0.49
     strum
    0.47
    haul
    0.47
     بجائے
    0.46
     না
    0.45
     bronze
    0.45
     security
    0.45
    Activations Density 0.000%

    No Known Activations