© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10291
    Prev
    Next
    INDEX
    Explanations

    narrative construction or voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    م
    3.41
    س
    2.73
    га
    2.53
    ो
    2.36
    म
    2.33
    м
    2.33
    ла
    2.30
    ต์
    2.30
    ात
    2.27
    ার
    2.14
    POSITIVE LOGITS
    Nella
    1.57
    茠
    1.55
     снижение
    1.55
    Vad
    1.54
    Nep
    1.52
     construido
    1.52
     Farrar
    1.50
     complicado
    1.48
     chois
    1.48
     tota
    1.48
    Activations Density 0.011%

    No Known Activations