© 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. 133529
    Prev
    Next
    INDEX
    Explanations

    home, away, radio, attic, normative, seniors

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

    probabilistic mechanics

    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
     sunny
    0.52
    ).
    0.44
    D
    0.42
     financially
    0.42
     disaster
    0.41
     Sonoma
    0.41
     volatile
    0.40
     bucket
    0.40
    Done
    0.40
     înv
    0.39
    POSITIVE LOGITS
     memungkinkan
    0.50
     entrevistas
    0.49
    GLAND
    0.48
    miktar
    0.48
     özelliği
    0.48
     матч
    0.48
    䥑
    0.47
     ****",
    0.47
    ریض
    0.47
    enek
    0.46
    Activations Density 0.000%

    No Known Activations