© 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. 5148
    Prev
    Next
    INDEX
    Explanations

    is followed by article

    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
    u
    1.63
    x
    1.56
    d
    1.48
    c
    1.47
    p
    1.47
    schaft
    1.27
    لا
    1.27
    g
    1.26
    囔
    1.23
    돠
    1.23
    POSITIVE LOGITS
     rearranging
    1.33
    ון
    1.32
     resounding
    1.30
    ্প
    1.30
     lift
    1.26
     चलिए
    1.23
     solving
    1.23
     이는
    1.22
     basins
    1.20
     fastening
    1.20
    Activations Density 0.140%

    No Known Activations