© 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. 25257
    Prev
    Next
    INDEX
    Explanations

    component arranged, keep everyone, condition

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

    search, check, and prepare yourself

    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
    !==
    0.48
     İslam
    0.46
     religión
    0.45
     ROUILLER
    0.45
    와이스
    0.45
    ИК
    0.44
     GIFT
    0.43
    ળ
    0.43
    스가
    0.42
     dacă
    0.42
    POSITIVE LOGITS
    aut
    0.50
    id
    0.49
     সংখ্য
    0.49
    anti
    0.49
     robust
    0.49
     Summary
    0.48
    N
    0.48
    assertion
    0.47
    summary
    0.47
    robust
    0.46
    Activations Density 0.000%

    No Known Activations