© 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. 231250
    Prev
    Next
    INDEX
    Explanations

    company and product names

    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
     আগমন
    0.50
     తరువాత
    0.48
    úra
    0.47
    क्षिप्त
    0.46
    军
    0.46
    близи
    0.45
     తర్వాత
    0.44
    áin
    0.44
     Webber
    0.43
     ওপ
    0.43
    POSITIVE LOGITS
    ↵↵
    0.63
     mone
    0.56
    в
    0.54
     =
    0.52
     paradigm
    0.48
     nodal
    0.46
     reagent
    0.45
     LIKE
    0.44
     guideline
    0.43
     sangue
    0.43
    Activations Density 0.001%

    No Known Activations