© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168260
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    np_acts-logits-general · gemini-2.5-flash-lite

    expressing thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    施術
    0.51
    ડિયા
    0.48
    シェア
    0.46
    齑
    0.46
     uprisings
    0.45
     infidelity
    0.44
     системати
    0.44
    єд
    0.44
     layoffs
    0.43
     оро
    0.43
    POSITIVE LOGITS
    <0x80>
    0.46
    unde
    0.46
    inc
    0.44
    the
    0.42
    mert
    0.42
     through
    0.41
    panorama
    0.41
     스
    0.41
     。,
    0.41
    unden
    0.40
    Activations Density 0.002%

    No Known Activations