© 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. 89871
    Prev
    Next
    INDEX
    Explanations

    league, film, culture, website

    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
     maliciously
    0.54
     wearables
    0.49
     m
    0.46
     м
    0.45
     wore
    0.44
     францу
    0.43
     philosophers
    0.43
     жизни
    0.43
     बैड
    0.43
    ュ
    0.42
    POSITIVE LOGITS
    explore
    0.54
    elijke
    0.50
    팰
    0.50
    رود
    0.48
    ่า
    0.47
    רים
    0.47
    PAssignment
    0.47
     bagi
    0.46
    chicken
    0.46
    tow
    0.45
    Activations Density 0.001%

    No Known Activations