© 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. 143626
    Prev
    Next
    INDEX
    Explanations

    offers, enables, causes

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

    offers, enables, provides

    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
     ČR
    0.44
     '
    0.44
       
    0.43
     attainment
    0.43
     ";"
    0.43
     "."
    0.43
     ('
    0.42
     }
    0.42
     np
    0.42
    POSITIVE LOGITS
     offrant
    0.59
     ofreci
    0.59
     रोमांच
    0.57
     ermöglicht
    0.55
     menawarkan
    0.55
     memungkinkan
    0.55
     ponú
    0.54
     khiến
    0.54
     waarbij
    0.54
     erbjuder
    0.54
    Activations Density 0.003%

    No Known Activations