© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    @

    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
    ৯
    2.56
    써
    2.36
    ン
    2.30
    न
    1.84
    욱
    1.80
    াঙ্গীর
    1.75
    INFRINGEMENT
    1.73
    ζει
    1.72
    ៌
    1.70
    जिटिव
    1.69
    POSITIVE LOGITS
    il
    2.67
    та
    2.58
    ри
    2.53
    ap
    2.45
    ad
    2.41
    ات
    2.30
    k
    2.27
    ate
    2.20
     Ciò
    2.16
    it
    2.14
    Activations Density 0.096%

    No Known Activations