© 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. 216669
    Prev
    Next
    INDEX
    Explanations

    list of words

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

    as in *

    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
    ک
    0.56
    MAP
    0.53
    af
    0.51
     hap
    0.51
    क
    0.47
     Abbe
    0.47
    ल
    0.46
    el
    0.46
    at
    0.45
    bro
    0.44
    POSITIVE LOGITS
     ошибка
    0.59
    鐗
    0.49
     سرطان
    0.49
     источник
    0.47
     Cheesecake
    0.46
     сигнала
    0.46
     сообщение
    0.45
     драй
    0.45
     сегодня
    0.44
     жүктөө
    0.44
    Activations Density 0.000%

    No Known Activations