© 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. 935
    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
     étudi
    0.80
     overheat
    0.78
     burnout
    0.77
     chat
    0.75
     troup
    0.75
    yzed
    0.75
    廃
    0.75
     rectMode
    0.74
     wakt
    0.74
     größte
    0.73
    POSITIVE LOGITS
    raising
    0.78
    ñ
    0.77
     Nigam
    0.71
    ṣ
    0.71
     NEWS
    0.69
     Sunday
    0.68
     Ghosh
    0.68
    refs
    0.67
    r
    0.67
    ഞ്
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.