© 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. 183925
    Prev
    Next
    INDEX
    Explanations

    spoken by

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

    * creates code, images

    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
    ?
    0.48
    uddin
    0.46
    স
    0.45
    it
    0.45
    #
    0.45
    Turn
    0.44
     Belly
    0.43
     the
    0.43
    Lab
    0.43
    Metric
    0.43
    POSITIVE LOGITS
     コード
    0.55
     நிதி
    0.53
     réparation
    0.51
    <unused713>
    0.50
     zabez
    0.50
     cellulaire
    0.50
     veoma
    0.50
     reconoce
    0.49
     financières
    0.48
     réflex
    0.48
    Activations Density 0.001%

    No Known Activations