© 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. 175158
    Prev
    Next
    INDEX
    Explanations

    tips, reports, distraction, fighter, credit

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

    greetings and 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
    ).
    0.48
    。
    0.47
    ە
    0.45
    ထ
    0.44
     Krankheit
    0.44
    ها
    0.43
     dangere
    0.43
     pokuš
    0.43
    ።
    0.42
     கடு
    0.41
    POSITIVE LOGITS
    នូវ
    0.52
     gastos
    0.49
    нести
    0.47
     воспользоваться
    0.47
    াচিত
    0.47
     utilizzare
    0.44
     সৌজন্য
    0.44
     atleast
    0.43
    薑
    0.42
    ip
    0.42
    Activations Density 0.000%

    No Known Activations