© 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. 219070
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    technical or administrative actions

    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
     disassembled
    0.47
    ሌ
    0.45
    夏
    0.42
    드렸
    0.41
    ल
    0.41
    ল
    0.40
     quinoa
    0.40
    斎
    0.40
     _{\
    0.39
     cyclospor
    0.39
    POSITIVE LOGITS
     huwa
    0.50
     daje
    0.47
     Debe
    0.47
     ପ୍ର
    0.46
     Babu
    0.46
     причина
    0.45
     Srbiji
    0.44
     problemi
    0.44
     Prabhu
    0.44
     индика
    0.42
    Activations Density 0.000%

    No Known Activations