© 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. 10991
    Prev
    Next
    INDEX
    Explanations

    bypass avoid skip

    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
    ina
    1.53
    ées
    1.45
    é
    1.41
    ни
    1.37
    to
    1.36
    لاً
    1.36
    man
    1.34
     définie
    1.34
    ary
    1.32
    μα
    1.32
    POSITIVE LOGITS
    e
    1.55
    忻
    1.41
     Mistakes
    1.38
    你了
    1.36
     Есть
    1.34
    eek
    1.32
     Gericht
    1.31
    ের
    1.30
    eers
    1.30
     evaded
    1.28
    Activations Density 0.119%

    No Known Activations