© 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. 83039
    Prev
    Next
    INDEX
    Explanations

    and invites, former licensed, million

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

    technical configuration and programming

    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
    жаю
    0.52
    ла
    0.49
     Elovl
    0.47
     ла
    0.47
     乀
    0.47
     thép
    0.47
    璁
    0.47
    aphyl
    0.46
    ларга
    0.46
    பிலோ
    0.46
    POSITIVE LOGITS
     Govern
    0.47
    দেখ
    0.45
    SNS
    0.42
    Gov
    0.41
    Driving
    0.40
    nina
    0.40
    S
    0.40
     Invitational
    0.40
    NRI
    0.40
     divulgação
    0.40
    Activations Density 0.000%

    No Known Activations