© 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. 42805
    Prev
    Next
    INDEX
    Explanations

    types of opposition or possession

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

    AS alias assignment

    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
    มัน
    0.50
     it
    0.47
    is
    0.47
    st
    0.46
    它
    0.44
    u
    0.43
    และ
    0.43
     и
    0.42
    ն
    0.42
    𝗶
    0.42
    POSITIVE LOGITS
     mahdoll
    0.45
     widers
    0.41
     rougeâtres
    0.41
     glaube
    0.40
     correctement
    0.40
     teilweise
    0.39
     pernyataan
    0.39
     bahsed
    0.38
     Mabel
    0.38
     sommige
    0.38
    Activations Density 0.000%

    No Known Activations