© 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. 54302
    Prev
    Next
    INDEX
    Explanations

    occurrences over time

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

    descriptions followed by implications

    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
     মোঃ
    0.56
    \
    0.54
     প্রদান
    0.50
     IN
    0.50
    하여
    0.49
     loosing
    0.47
     সকল
    0.46
     &
    0.45
     &/
    0.45
    !!!
    0.45
    POSITIVE LOGITS
     मसलन
    0.61
     yüzde
    0.60
     roughly
    0.59
     etcétera
    0.59
    roughly
    0.57
     словам
    0.56
     quizá
    0.55
     нынеш
    0.55
    他说
    0.51
     примерно
    0.50
    Activations Density 0.212%

    No Known Activations