© 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. 1324
    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
    psilon
    0.86
     règ
    0.73
     Règ
    0.71
    俗
    0.67
     alegre
    0.66
    랑
    0.66
    ギュ
    0.63
    Humans
    0.63
     cancels
    0.63
    츤
    0.63
    POSITIVE LOGITS
     निगरानी
    0.88
     دیگر
    0.85
     ܠ
    0.84
     पुजारी
    0.84
     появились
    0.79
     کند
    0.78
    #__
    0.77
     другом
    0.77
    至於
    0.77
     πολύ
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.