© 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. 25251
    Prev
    Next
    INDEX
    Explanations

    leading punctuation and code structures

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

    markup or code context

    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
     sinuses
    0.49
    보
    0.47
     ears
    0.47
     erections
    0.47
    ב
    0.47
    ată
    0.46
    种
    0.46
    ęd
    0.45
    щают
    0.44
    ърква
    0.44
    POSITIVE LOGITS
     kontinuier
    0.46
     financi
    0.42
     ))
    0.42
     KYC
    0.41
     தானே
    0.41
     Kohn
    0.39
     )}
    0.38
     Compañ
    0.38
    paren
    0.38
     ){
    0.38
    Activations Density 0.000%

    No Known Activations