© 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. 107514
    Prev
    Next
    INDEX
    Explanations

    his + noun

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

    possessive pronoun followed by descriptor

    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
     finde
    0.30
    𝔱
    0.29
    ত্যার
    0.28
    जारत
    0.28
    ၻ
    0.28
    izielle
    0.27
    defeat
    0.27
     définie
    0.27
    ᥣ
    0.27
    Tenemos
    0.27
    POSITIVE LOGITS
    0.38
     примерно
    0.28
     hapless
    0.28
    <0xAC>
    0.28
     volatile
    0.28
     ≈
    0.27
     crumpled
    0.27
    ≈
    0.27
     dozen
    0.27
    лению
    0.27
    Activations Density 0.123%

    No Known Activations