© 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. 84726
    Prev
    Next
    INDEX
    Explanations

    French film

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

    describing, ordering, or presenting arguments

    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
     хочется
    0.47
     продолжает
    0.47
     подходя
    0.46
    rootScope
    0.45
    埜
    0.45
     総
    0.44
     смартфон
    0.43
     стар
    0.43
     संघर्ष
    0.43
     баста
    0.43
    POSITIVE LOGITS
     Luxe
    0.52
     calcareous
    0.50
     balsamic
    0.48
     waxing
    0.48
     prawns
    0.45
     embell
    0.44
    ި
    0.44
     prawn
    0.43
     Immunohist
    0.43
    oggetto
    0.43
    Activations Density 0.000%

    No Known Activations