© 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. 50558
    Prev
    Next
    INDEX
    Explanations

    named entities and specific nouns

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

    numbers and lists

    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
     દરમ
    0.30
    जलवायु
    0.29
     фев
    0.28
    niOkno
    0.28
    <unused971>
    0.28
     фир
    0.27
     ресу
    0.26
    𐰖
    0.26
     ઉત્પાદ
    0.26
    isOnTimer
    0.26
    POSITIVE LOGITS
     the
    0.33
     black
    0.29
    -
    0.25
     Django
    0.25
     back
    0.24
     أ
    0.24
     Play
    0.24
     up
    0.24
     to
    0.23
     image
    0.23
    Activations Density 0.127%

    No Known Activations