© 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. 2861
    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
     still
    0.80
     ancora
    0.77
     aún
    0.72
     todavía
    0.67
     masih
    0.67
    Still
    0.66
    となった
    0.66
    仍
    0.66
     ještě
    0.65
     아직
    0.65
    POSITIVE LOGITS
     since
    1.21
     Since
    1.03
    since
    1.01
     Depuis
    0.95
     lately
    0.95
     sejak
    0.91
    Since
    0.90
     منذ
    0.90
     Desde
    0.88
     Been
    0.85
    Activations Density 0.080%

    No Known Activations