© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54056
    Prev
    Next
    INDEX
    Explanations

    names starting with Lee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
     опла
    0.40
    "]);
    0.39
    نی
    0.38
    <0x94>
    0.38
    ভূ
    0.37
    -])
    0.37
    شتی
    0.37
     অর্থাৎ
    0.37
    ओं
    0.36
     outcomes
    0.36
    POSITIVE LOGITS
    uwen
    0.63
    per
    0.56
     李
    0.54
    Lee
    0.47
     korean
    0.44
     Lee
    0.41
     lee
    0.40
    Ann
    0.40
     韓国
    0.40
     Korean
    0.39
    Activations Density 0.006%

    No Known Activations