© 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. 208303
    Prev
    Next
    INDEX
    Explanations

    sports, time, and ordinal numbers

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

    multidisciplinary topics, manual extraction, variables

    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
    hyth
    0.51
    ಓ
    0.50
    ោម
    0.49
    ě
    0.49
    loid
    0.48
    蠶
    0.47
    য়ের
    0.46
     夜
    0.46
    jols
    0.46
    ನ
    0.46
    POSITIVE LOGITS
     interdiscipl
    0.54
    兴
    0.45
     intelekt
    0.44
     μετα
    0.44
     υπηρε
    0.42
     multidiscipl
    0.41
     συμμε
    0.41
     incumb
    0.41
     memanfaatkan
    0.41
     ditetapkan
    0.40
    Activations Density 0.001%

    No Known Activations