© 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. 197529
    Prev
    Next
    INDEX
    Explanations

    images, products, girl

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

    avoiding extrapolation

    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
    ער
    0.59
    лі
    0.54
    排列
    0.54
    лу
    0.53
    此刻
    0.52
    ем
    0.50
    漣
    0.50
    મ
    0.50
    му
    0.49
    كة
    0.49
    POSITIVE LOGITS
     violently
    0.45
     treasured
    0.42
     peacefully
    0.42
     Deity
    0.41
     entour
    0.40
    heri
    0.40
     বিরোধী
    0.40
     회사
    0.40
     सौंप
    0.40
     చెప్పారు
    0.40
    Activations Density 0.000%

    No Known Activations