© 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. 4503
    Prev
    Next
    INDEX
    Explanations

    emojis or "with the"

    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
     publicit
    0.96
     dialects
    0.93
     dashing
    0.92
    呓
    0.90
     anticon
    0.89
    讪
    0.87
     jagged
    0.86
     mischief
    0.86
     heady
    0.85
     inciting
    0.85
    POSITIVE LOGITS
    -
    1.38
    ❤
    1.35
    ❤️
    1.23
    paren
    1.15
    💞
    1.13
    and
    1.09
    ind
    1.05
    ♥
    1.05
    ❤️❤️
    1.03
    с
    1.02
    Activations Density 0.695%

    No Known Activations