© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105380
    Prev
    Next
    INDEX
    Explanations

    mission of, can come, simply neglect, standard living, modern dentistry, supplemental income

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

    controlling abusive behavior

    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
    各種
    0.46
    冠军
    0.46
    歐
    0.45
    密钥
    0.44
    데이
    0.43
    滨
    0.43
    叡
    0.43
    ನ್ನ
    0.43
     .{
    0.43
    卖家
    0.42
    POSITIVE LOGITS
     bør
    0.46
     üçüncü
    0.45
    력을
    0.43
     perpend
    0.43
     exagger
    0.42
     वापरा
    0.42
     povol
    0.42
     zakres
    0.41
    halt
    0.41
    යට
    0.41
    Activations Density 0.000%

    No Known Activations