© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7980
    Prev
    Next
    INDEX
    Explanations

    data types followed by keywords

    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
    punkt
    1.88
    tı
    1.88
    light
    1.77
    regation
    1.74
    person
    1.66
    ت
    1.63
    kan
    1.62
    1
    1.57
    ductory
    1.54
    on
    1.52
    POSITIVE LOGITS
     kuwa
    1.52
     وعلى
    1.50
    𝓮
    1.34
    祂
    1.29
    ᴅ
    1.19
    ان
    1.17
    🅔
    1.17
    Му
    1.16
    𝘏
    1.16
     dwa
    1.16
    Activations Density 0.098%

    No Known Activations