© 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. 8769
    Prev
    Next
    INDEX
    Explanations

    non-latin script words

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

    command or input

    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
     бор
    0.48
     дву
    0.48
     Oba
    0.48
    恐
    0.47
     cardamom
    0.46
    edik
    0.46
     Obi
    0.45
     Ã
    0.45
    お得
    0.44
     अतिथि
    0.44
    POSITIVE LOGITS
     रुका
    0.48
    ून
    0.46
     سطح
    0.46
    றும்
    0.45
    blockList
    0.45
    isl
    0.44
     শহর
    0.43
    سط
    0.42
     জুড়ে
    0.42
    ாலும்
    0.42
    Activations Density 0.000%

    No Known Activations