© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    C++ standard library features

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

    risk and reward

    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
     Soak
    0.46
     茶
    0.45
    CIA
    0.45
     CIA
    0.44
    تقد
    0.43
    Tart
    0.43
     tart
    0.43
     家具
    0.43
     非
    0.42
     terl
    0.41
    POSITIVE LOGITS
    ان
    0.54
     each
    0.50
     aligns
    0.49
     जाएगा
    0.48
     adjusts
    0.45
     instructs
    0.45
     communicates
    0.45
    दोनों
    0.44
     returnPacket
    0.44
     duplicates
    0.43
    Activations Density 0.000%

    No Known Activations