© 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-16K
    7. 4862
    Prev
    Next
    INDEX
    Explanations

    EmiBot imitation

    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_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
    ם
    3.69
    ました
    3.61
    ni
    3.27
    ため
    3.13
    la
    2.95
    ন
    2.95
    son
    2.92
    st
    2.78
    ly
    2.78
    nya
    2.75
    POSITIVE LOGITS
    деся
    2.94
    ু
    2.52
    ſs
    2.50
    ん
    2.47
    ी
    2.41
    ście
    2.39
    ñones
    2.30
    planes
    2.22
    ší
    2.20
    ção
    2.19
    Activations Density 0.406%

    No Known Activations