© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7848
    Prev
    Next
    INDEX
    Explanations

    responses from model

    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_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
    ick
    0.56
    Discover
    0.55
    लोड
    0.54
    동
    0.54
    throat
    0.53
    GM
    0.52
    பாய்
    0.51
    wick
    0.51
    osexual
    0.51
     ▪
    0.50
    POSITIVE LOGITS
     I
    0.64
     අය
    0.54
     Innovative
    0.53
     duur
    0.52
    リモ
    0.52
     Champaign
    0.52
    ूंगा
    0.51
     lai
    0.51
     রেজিস্ট্র
    0.51
     माननीय
    0.51
    Activations Density 0.089%

    No Known Activations