© 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. 196647
    Prev
    Next
    INDEX
    Explanations

    patent identifiers and file types

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

    data acquisition and functions

    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
    di
    0.52
    tha
    0.50
    connect
    0.49
    diocese
    0.48
    ྜ
    0.46
    டை
    0.46
    estep
    0.45
    די
    0.44
    brane
    0.43
    ड्रो
    0.43
    POSITIVE LOGITS
     സ്വാതന്ത്ര
    0.48
     પડ
    0.47
     流
    0.46
     رح
    0.44
     Анти
    0.44
     ле
    0.43
     လ
    0.43
     служ
    0.43
     古
    0.43
     свободно
    0.43
    Activations Density 0.000%

    No Known Activations