© 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. 200598
    Prev
    Next
    INDEX
    Explanations

    outbound grain, Victorian era, get away

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

    prime, application, palindrome

    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
    nab
    0.50
    cev
    0.49
     imagen
    0.45
     murmur
    0.44
    ێر
    0.43
    ن
    0.43
    atas
    0.43
    不少
    0.42
    ل
    0.42
    nature
    0.42
    POSITIVE LOGITS
    дикатор
    0.48
     हात
    0.45
     Khartoum
    0.45
    였다
    0.44
    ߋ
    0.44
     Лон
    0.43
    ಾವ್
    0.43
    錨
    0.43
     PlayerSelector
    0.43
     equivalently
    0.42
    Activations Density 0.001%

    No Known Activations