© 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. 84353
    Prev
    Next
    INDEX
    Explanations

    gazelle, World site

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

    App Service, dialogue, relying, Polygon, accounts, loop

    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
    hovah
    0.55
    ހ
    0.52
    hada
    0.51
    RDS
    0.47
    hAP
    0.46
    orado
    0.46
    ভার
    0.45
    IQUE
    0.45
    檤
    0.45
    LETE
    0.45
    POSITIVE LOGITS
     сайт
    0.50
     ей
    0.46
     зару
    0.45
     signifies
    0.45
     ተመሳሳይ
    0.44
     sequestration
    0.43
     seag
    0.42
     Myerson
    0.42
     статті
    0.42
     ця
    0.42
    Activations Density 0.000%

    No Known Activations