© 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. 218870
    Prev
    Next
    INDEX
    Explanations

    ordering checklists recipe accepted Returns

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

    Describes states or movement

    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
     Initiatives
    0.50
     T
    0.49
     ABI
    0.49
     Environment
    0.49
     Installations
    0.49
     up
    0.48
     Primary
    0.48
     Iberian
    0.48
     Aj
    0.47
     Espan
    0.47
    POSITIVE LOGITS
     कनेक्टिव
    0.52
     захворю
    0.48
    痔
    0.46
    ото
    0.46
    ံ့
    0.46
    柵
    0.45
    GALAD
    0.44
    AZIONE
    0.44
    了承
    0.44
    OLYBDENUM
    0.44
    Activations Density 0.001%

    No Known Activations