© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2851
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ローバル
    0.68
     Coverage
    0.61
     Appointments
    0.60
     contractual
    0.59
     Defaults
    0.58
    👔
    0.58
    вторых
    0.57
    谥
    0.57
     Corporate
    0.56
    isie
    0.55
    POSITIVE LOGITS
     DIY
    2.20
    DIY
    2.14
     diy
    1.73
     hobby
    1.65
    diy
    1.63
     amateur
    1.61
     homemade
    1.50
    Homemade
    1.39
     experimenting
    1.34
     experimentation
    1.33
    Activations Density 1.668%

    No Known Activations