© 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. 57063
    Prev
    Next
    INDEX
    Explanations

    Creates instance, gets data

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

    code keywords and programming structures

    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
     interne
    0.60
    ז
    0.60
    推定
    0.59
     murderous
    0.55
     nihil
    0.54
     demonic
    0.53
     automat
    0.52
    kosten
    0.52
     menacing
    0.52
    אָ
    0.50
    POSITIVE LOGITS
    io
    0.51
    ...");
    0.47
     String
    0.46
    获取
    0.46
    android
    0.45
    parser
    0.45
    getLogger
    0.45
     ...,
    0.45
     HttpServlet
    0.44
     {
    0.44
    Activations Density 0.013%

    No Known Activations