© 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. 201937
    Prev
    Next
    INDEX
    Explanations

    (PCJ) Open Road Package

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

    reduces stress and matrix multiplication

    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
    
    0.52
     Hintergrund
    0.50
    ي
    0.48
     Verbind
    0.47
     Porta
    0.46
     EIA
    0.46
     Theorie
    0.45
    
    0.45
     antib
    0.45
    لمين
    0.45
    POSITIVE LOGITS
     làm
    0.48
    acją
    0.47
     racing
    0.46
     máu
    0.46
     stepper
    0.46
     sparking
    0.45
     बॉस
    0.45
    पीएससी
    0.45
     racquet
    0.44
     bursts
    0.44
    Activations Density 0.002%

    No Known Activations