© 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. 184264
    Prev
    Next
    INDEX
    Explanations

    pray for dialogue

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

    common priesthood of believers

    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
     প্রচলিত
    0.48
    变化
    0.46
    Updates
    0.45
    MOVIE
    0.44
    Попис
    0.44
     assuntos
    0.43
    엠
    0.43
     टूटा
    0.42
    阐
    0.42
    Deferred
    0.41
    POSITIVE LOGITS
    untza
    0.44
    ía
    0.42
    ería
    0.42
     Perugia
    0.42
    acidad
    0.41
    ña
    0.41
    erà
    0.40
    мія
    0.40
     
    0.40
    
    0.40
    Activations Density 0.011%

    No Known Activations