© 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. 234442
    Prev
    Next
    INDEX
    Explanations

    events may qualify

    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
    ラ
    0.57
    의
    0.56
    的
    0.55
     which
    0.53
     card
    0.51
    の
    0.50
    は
    0.47
    я
    0.47
    का
    0.47
    카드
    0.47
    POSITIVE LOGITS
    iskup
    0.61
    ändigen
    0.51
    uillez
    0.50
    ísk
    0.49
     overpowering
    0.47
    attere
    0.47
    idase
    0.45
     می‌کند
    0.45
     hassles
    0.45
     bottlenecks
    0.44
    Activations Density 0.001%

    No Known Activations