© 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. 148060
    Prev
    Next
    INDEX
    Explanations

    adopt or burial or general

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

    potential of gain

    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
     beraber
    0.42
     bazı
    0.42
    ριά
    0.41
     souffle
    0.41
    ন্ত্রী
    0.41
    并
    0.41
    並
    0.40
    
    0.40
    声
    0.40
     dupa
    0.40
    POSITIVE LOGITS
    ics
    0.47
    atot
    0.43
    inol
    0.42
    ेशन
    0.42
    og
    0.42
     ডিজি
    0.42
     Worker
    0.42
    write
    0.41
    okes
    0.41
    in
    0.40
    Activations Density 0.001%

    No Known Activations