© 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. 238946
    Prev
    Next
    INDEX
    Explanations

    keywords followed by specific descriptors

    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
    تاج
    0.52
    萑
    0.49
    팅
    0.48
    тов
    0.48
    وزيع
    0.48
    тору
    0.48
    اتو
    0.47
     நிமிட
    0.46
    प्रोड
    0.46
    이트
    0.46
    POSITIVE LOGITS
     opposites
    0.46
    s
    0.46
     obligated
    0.44
    ,
    0.44
     GIT
    0.43
     indicar
    0.43
     BONDS
    0.43
     INR
    0.41
     Sunderland
    0.40
    c
    0.40
    Activations Density 0.000%

    No Known Activations