© 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. 133453
    Prev
    Next
    INDEX
    Explanations

    Wordpress custom features

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

    empathy, buttons, releasing, breaking

    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
    ร
    0.50
    ۷
    0.48
    รู้
    0.47
     செல்சிய
    0.47
    ي
    0.46
    พย์
    0.46
     ۷
    0.46
    DO
    0.46
    EK
    0.45
    ellite
    0.43
    POSITIVE LOGITS
     中央
    0.53
    ော်
    0.50
     Haut
    0.48
     már
    0.48
    仲
    0.47
     melden
    0.47
     audiov
    0.47
    h
    0.47
     mám
    0.47
     ruimte
    0.46
    Activations Density 0.000%

    No Known Activations