© 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. 149012
    Prev
    Next
    INDEX
    Explanations

    ", we"

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

    private keyword

    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
    材質
    0.44
     हमें
    0.41
     меры
    0.40
    て
    0.39
    fly
    0.39
     Mathematical
    0.39
    custList
    0.39
    已
    0.39
    etik
    0.38
     explicación
    0.38
    POSITIVE LOGITS
     confortable
    0.50
     weary
    0.42
     potřeb
    0.41
     Toolbar
    0.41
    人士
    0.39
     bric
    0.38
    inim
    0.38
     आरामदायक
    0.37
    
    0.37
     "@/
    0.37
    Activations Density 0.000%

    No Known Activations