© 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. 40850
    Prev
    Next
    INDEX
    Explanations

    Justin followed by a name

    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
    ра
    2.14
    ா
    2.14
    ل
    2.09
    ان
    2.06
    ו
    1.98
    塹
    1.98
    ר
    1.97
    ре
    1.93
    ет
    1.92
    𝕤
    1.88
    POSITIVE LOGITS
    t
    2.44
    い
    2.44
    től
    2.36
    ak
    2.13
    ur
    2.05
    ı
    2.02
    um
    1.95
     peine
    1.92
     וב
    1.92
    is
    1.90
    Activations Density 0.001%

    No Known Activations