© 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. 1222
    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
     circa
    0.65
     convenient
    0.63
     parabolic
    0.63
     personable
    0.63
     no
    0.60
     в
    0.59
     westerly
    0.59
     nelle
    0.59
     mittens
    0.59
     nell
    0.58
    POSITIVE LOGITS
    ود
    0.82
    ور
    0.80
    وم
    0.77
    ش
    0.75
    وا
    0.71
     أم
    0.69
    ض
    0.69
    ُ
    0.67
    Puedes
    0.67
    ية
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.