© 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. 61120
    Prev
    Next
    INDEX
    Explanations

    you can

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

    multilingual phrases and formatting

    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
     gelecek
    0.46
    니다
    0.44
    fect
    0.44
    aden
    0.41
    서
    0.41
    infect
    0.40
    atang
    0.40
    oren
    0.39
    ikka
    0.39
     ho
    0.39
    POSITIVE LOGITS
     Zust
    0.53
    队伍
    0.50
     bądź
    0.50
    ♝
    0.48
     이게
    0.48
     executar
    0.48
    に基づいて
    0.47
     fazendo
    0.47
     لڑ
    0.47
     fazer
    0.46
    Activations Density 0.000%

    No Known Activations