© 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. 1588
    Prev
    Next
    INDEX
    Explanations

    modelversions, beta, recovery

    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
     sparing
    0.76
     snacking
    0.72
     insulating
    0.70
    தந்திர
    0.69
    \/}
    0.68
     multiplets
    0.68
     sheeting
    0.68
     annuities
    0.66
     polytopes
    0.66
     buty
    0.65
    POSITIVE LOGITS
    T
    1.20
    R
    1.11
    E
    1.10
    J
    1.09
    W
    1.08
    L
    1.07
    C
    1.05
    M
    1.05
    II
    1.04
    N
    1.04
    Activations Density 0.147%

    No Known Activations