© 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. 13055
    Prev
    Next
    INDEX
    Explanations

    over a time period

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

    over time

    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
    恙
    0.49
     lifespan
    0.42
     Thus
    0.39
    ↵↵
    0.39
    Within
    0.39
     bờ
    0.39
    P
    0.39
    リ
    0.38
    Gu
    0.38
     Within
    0.38
    POSITIVE LOGITS
    linkCell
    0.49
     শ্রদ্ধ
    0.44
     زینت
    0.44
    
    0.42
    security
    0.41
    😷
    0.41
    窸
    0.41
     جگہ
    0.40
    混凝
    0.40
    unpriv
    0.40
    Activations Density 0.000%

    No Known Activations