© 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. 224658
    Prev
    Next
    INDEX
    Explanations

    Address formatting

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

    state estimation and software identification

    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
     Лу
    0.54
    t
    0.50
    وم
    0.45
    发射
    0.44
     гром
    0.44
    ἵ
    0.44
    型号
    0.44
    一
    0.44
    ิล
    0.44
     bulldog
    0.44
    POSITIVE LOGITS
     DNIs
    0.47
     undetectable
    0.45
     জাতিসঙ্ঘ
    0.45
    សម្រាប់ការ
    0.44
     unimplemented
    0.44
    January
    0.41
     ihres
    0.40
     gegen
    0.40
     anonymity
    0.39
    バラ
    0.39
    Activations Density 0.003%

    No Known Activations