© 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. 206611
    Prev
    Next
    INDEX
    Explanations

    connection and, evolutionary theory

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

    excluding flights

    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
    ch
    0.49
    Buenos
    0.45
    “
    0.45
    gn
    0.44
    ك
    0.44
    Texas
    0.43
    k
    0.43
    இ
    0.43
    ل
    0.43
    άν
    0.42
    POSITIVE LOGITS
    тились
    0.52
     oligodend
    0.52
     квадрат
    0.52
     signboard
    0.51
    پيديا
    0.50
     colonialism
    0.50
     monop
    0.50
     alignItems
    0.49
     plabic
    0.49
     SEPTEMBER
    0.49
    Activations Density 0.001%

    No Known Activations