© 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. 60211
    Prev
    Next
    INDEX
    Explanations

    CE Mark certification

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

    why, item descriptions, not try

    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
    н
    0.56
    ၜ
    0.50
    цеп
    0.48
    ﺷ
    0.48
    <0xEB>
    0.47
     Madagascar
    0.46
    يمكن
    0.46
    શ્વ
    0.46
     Placeholder
    0.46
     Ма
    0.45
    POSITIVE LOGITS
     {
    0.50
     ambivalent
    0.48
     =)
    0.48
     遊ん
    0.47
     tasting
    0.46
     budding
    0.46
     genre
    0.46
     ){
    0.45
    Aryan
    0.45
    vora
    0.44
    Activations Density 0.000%

    No Known Activations