© 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. 25255
    Prev
    Next
    INDEX
    Explanations

    specific categories

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

    core concepts and operations

    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
    伫
    0.49
     dialed
    0.49
    特点
    0.48
    自分
    0.47
    这时
    0.47
    人
    0.47
    人群
    0.45
    氩
    0.43
    类别
    0.43
    тор
    0.42
    POSITIVE LOGITS
    ր
    0.44
     захворю
    0.44
     আত্ম
    0.43
    qh
    0.42
     potentialities
    0.42
     Ergebn
    0.42
     lf
    0.42
     GoName
    0.42
     זו
    0.41
     inducing
    0.41
    Activations Density 0.000%

    No Known Activations