© 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. 52255
    Prev
    Next
    INDEX
    Explanations

    food, drink, or meals

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

    ethically questionable

    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
    यानक
    0.50
     자동차
    0.47
    そも
    0.46
     polož
    0.46
     නිර්
    0.45
    ট
    0.45
    Ტ
    0.45
     tessuto
    0.45
     médicaments
    0.45
     ಜೊ
    0.44
    POSITIVE LOGITS
     Village
    0.46
    8
    0.45
    9
    0.41
     Sometimes
    0.41
    ,
    0.40
    7
    0.39
     Education
    0.38
     Memorandum
    0.38
     Specimens
    0.38
     Educación
    0.38
    Activations Density 0.000%

    No Known Activations