© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    million quantities

    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
    ној
    1.78
    인
    1.62
    ਰਾ
    1.60
    ни
    1.57
    산업
    1.57
    க
    1.53
    но
    1.52
    ectable
    1.52
    알
    1.48
    accueil
    1.47
    POSITIVE LOGITS
    ない
    2.03
    n
    1.99
    nge
    1.92
    gie
    1.91
    nent
    1.84
    nél
    1.79
    nte
    1.77
    nings
    1.76
    nak
    1.73
    nj
    1.73
    Activations Density 0.026%

    No Known Activations