© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13785
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    ي
    0.82
     command
    0.74
     catalogue
    0.67
     unfor
    0.66
     surrounding
    0.66
     impossibility
    0.66
     $
    0.65
    y
    0.65
     helpful
    0.64
     হয়ত
    0.64
    POSITIVE LOGITS
    eleaf
    0.87
    }^{*}
    0.83
     paralelo
    0.83
    gekehrt
    0.80
     AssetImage
    0.79
    ೫
    0.79
    れい
    0.77
     multiplicado
    0.77
    ୭
    0.75
    knee
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.