© 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. 227063
    Prev
    Next
    INDEX
    Explanations

    lawyers, Supply Chain, Label, Reception security

    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
     Änderungen
    0.48
    ଁ
    0.46
    เต
    0.46
     polytopes
    0.46
     äh
    0.45
     Jake
    0.45
     अधिकतर
    0.45
     Fukushima
    0.44
    ière
    0.44
     übernimmt
    0.44
    POSITIVE LOGITS
    as
    0.52
                    
    0.51
    ER
    0.50
                   
    0.47
    Eas
    0.47
     )-
    0.47
    之
    0.47
    install
    0.46
    within
    0.46
                       
    0.46
    Activations Density 0.000%

    No Known Activations