© 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. 14119
    Prev
    Next
    INDEX
    Explanations

    Bron/Anton/Elon/Ron + suffix

    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
    gruppe
    2.48
    ҙ
    2.41
    toc
    2.31
    んは
    2.31
    tag
    2.28
    ar
    2.27
    tone
    2.27
    ीय
    2.25
    tie
    2.20
    tween
    2.20
    POSITIVE LOGITS
    ر
    2.47
    م
    2.38
    nnnn
    2.27
    м
    2.22
    呐
    2.22
    да
    2.13
    ificance
    2.08
     behalf
    2.05
    с
    2.05
    et
    2.03
    Activations Density 0.234%

    No Known Activations