© 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. 131194
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    list items and descriptions

    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
    鲇
    0.59
     Wrocław
    0.47
    ет
    0.45
     ರಾಜ
    0.44
    缅
    0.44
    鮎
    0.43
    實現
    0.43
     Ét
    0.43
     ಸೇ
    0.43
     Eugenia
    0.43
    POSITIVE LOGITS
    oxa
    0.46
    kva
    0.46
    ב
    0.46
    ahas
    0.44
    kra
    0.44
    রিত
    0.44
    baud
    0.44
    מ
    0.44
    b
    0.43
    omm
    0.42
    Activations Density 0.000%

    No Known Activations