© 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. 1997
    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
     veze
    0.77
     vestiges
    0.73
     concerted
    0.72
     forceful
    0.72
    ુ
    0.70
     dissident
    0.68
     imaginary
    0.68
     dostępne
    0.68
     regiões
    0.67
     hypothesized
    0.66
    POSITIVE LOGITS
    م
    0.83
    Cread
    0.82
    arán
    0.77
    aldo
    0.76
    ᒪ
    0.76
    ar
    0.75
    Bytes
    0.75
    ó
    0.74
    ला
    0.73
    or
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.