© 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. 4122
    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
    L
    0.80
    מ
    0.79
    Т
    0.76
    T
    0.75
    N
    0.75
    M
    0.74
    라고
    0.71
    t
    0.70
    C
    0.68
    일
    0.67
    POSITIVE LOGITS
     assemblages
    0.67
     autrefois
    0.66
     barbit
    0.64
     dislocations
    0.63
     boutiques
    0.56
     cerebrospinal
    0.55
     domest
    0.55
     quarant
    0.55
     bölün
    0.55
     rivets
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.