© 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-262K
    7. 10971
    Prev
    Next
    INDEX
    Explanations

    decorate, decorated, decorating, decoration

    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_262k_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
    ت
    2.25
    ます
    2.16
    з
    2.06
    تها
    2.03
    tır
    2.02
    нда
    1.83
    ત
    1.81
    त
    1.80
    ті
    1.70
    缈
    1.70
    POSITIVE LOGITS
    c
    2.64
    ار
    2.36
    iv
    2.31
    cps
    2.30
    n
    2.20
    is
    2.19
     Tregs
    2.16
    oncer
    2.14
     waveguides
    2.14
     surm
    2.14
    Activations Density 0.005%

    No Known Activations