© 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. 232126
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign characters

    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
     rifiuti
    0.42
    )!
    0.41
    也就是说
    0.41
     tjen
    0.40
    贿
    0.40
     motivator
    0.39
    ؟!
    0.39
     berbahaya
    0.39
     leth
    0.39
     byen
    0.39
    POSITIVE LOGITS
     two
    0.46
    兩
    0.45
    two
    0.44
    עי
    0.44
    ea
    0.44
     една
    0.43
    ą
    0.43
    いた
    0.42
     cả
    0.41
    这两
    0.41
    Activations Density 0.005%

    No Known Activations