© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14969
    Prev
    Next
    INDEX
    Explanations

    almost as

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

    technical discussions and code snippets

    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
     
    0.67
     LIVE
    0.54
     penalty
    0.54
     UAE
    0.49
     system
    0.48
     cheaper
    0.48
     시간
    0.48
    d
    0.47
     upfront
    0.47
     very
    0.47
    POSITIVE LOGITS
    叅
    0.49
     proz
    0.48
    ۴
    0.48
    袅
    0.48
    高志森
    0.48
    Geschichte
    0.47
    ಿಕೊಂಡು
    0.47
    mySocket
    0.46
    个人的
    0.46
    总统
    0.45
    Activations Density 0.000%

    No Known Activations