© 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. 203373
    Prev
    Next
    INDEX
    Explanations

    posting this ideas

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

    foreign languages and medical conditions

    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
     ಅನುಪ
    0.53
    elaide
    0.48
     ಕಂಚ
    0.47
     "#{
    0.46
    xiii
    0.45
     above
    0.45
     attitudes
    0.45
     亠
    0.42
     Abstand
    0.42
     cobalt
    0.42
    POSITIVE LOGITS
    ционных
    0.50
    хих
    0.49
     Cleaner
    0.47
    ्युन
    0.47
    ні
    0.45
    Tiene
    0.44
    เวอร์
    0.44
     Dunk
    0.44
    Cleaner
    0.44
    𝐋
    0.43
    Activations Density 0.001%

    No Known Activations