© 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. 242161
    Prev
    Next
    INDEX
    Explanations

    went with or time duration

    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
     Шрифт
    0.54
     पैमाने
    0.53
    هاي
    0.52
     জমিদার
    0.49
    鲮
    0.49
     क्रीम
    0.48
     البيانات
    0.48
     خار
    0.47
    겠지만
    0.47
     എതി
    0.46
    POSITIVE LOGITS
    u
    0.63
    MAY
    0.47
    Cur
    0.46
    Species
    0.46
    =@@
    0.45
    hemat
    0.44
    g
    0.44
    A
    0.44
    TOM
    0.43
    uhe
    0.43
    Activations Density 0.002%

    No Known Activations