© 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. 102544
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

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

    term or evening

    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
    il
    0.70
    as
    0.64
    ine
    0.63
    ol
    0.63
    comes
    0.61
    ut
    0.60
    y
    0.59
    os
    0.58
    é
    0.57
    is
    0.56
    POSITIVE LOGITS
    介绍了
    0.50
     فوټبال
    0.49
    ಲ್ಯಾ
    0.48
    정보
    0.47
     understanding
    0.47
     naught
    0.45
     muhimu
    0.45
     discre
    0.45
    مر
    0.45
     respectivamente
    0.44
    Activations Density 0.001%

    No Known Activations