© 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. 29438
    Prev
    Next
    INDEX
    Explanations

    free trial days

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

    free trial days

    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
    ש
    0.54
    я
    0.52
    ४
    0.52
    ту
    0.50
    ш
    0.50
    餐厅
    0.49
    τα
    0.48
    스
    0.48
    తుందని
    0.47
    Dining
    0.47
    POSITIVE LOGITS
     Via
    0.45
     rejoint
    0.44
     Ull
    0.44
     Doc
    0.43
     ร่วม
    0.43
     viennent
    0.43
     furious
    0.42
     ചെയ്തു
    0.42
     Experienced
    0.42
     Avec
    0.42
    Activations Density 0.002%

    No Known Activations