© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42518
    Prev
    Next
    INDEX
    Explanations

    completed, now, understanding, dividing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    陇
    0.50
    隴
    0.44
    烜
    0.40
    isance
    0.39
     Nagel
    0.38
    涧
    0.37
    ੯
    0.37
    लंघन
    0.37
     Tyl
    0.35
    棂
    0.35
    POSITIVE LOGITS
     cpt
    0.40
     masch
    0.39
     repayments
    0.39
     capi
    0.39
    Pict
    0.39
    ructures
    0.39
     romances
    0.38
     חיי
    0.38
    婊
    0.38
    shares
    0.38
    Activations Density 0.001%

    No Known Activations