© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    driver for linux

    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
    ي
    2.69
    ি
    2.45
    л
    2.42
    й
    2.38
    м
    2.25
    ছেন
    2.13
     tượng
    2.09
    ित्र
    2.06
    ্ঞ
    2.03
    いった
    2.03
    POSITIVE LOGITS
    schaft
    3.36
    ات
    3.11
    ר
    3.09
    s
    2.94
    ς
    2.80
    ્સ
    2.75
    ა
    2.70
    ു
    2.69
    ра
    2.63
    sx
    2.53
    Activations Density 0.368%

    No Known Activations