© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    possessive after person

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

    possessive nouns

    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
    CR
    0.22
    4
    0.21
    3
    0.21
    structure
    0.20
    6
    0.20
     préférence
    0.20
    g
    0.20
    nw
    0.20
    我們
    0.20
    ou
    0.20
    POSITIVE LOGITS
    们的
    0.24
     ihrem
    0.23
     wholeheartedly
    0.22
     каж
    0.21
    たちの
    0.21
     during
    0.20
     фра
    0.20
     в
    0.20
    фор
    0.20
     прямо
    0.20
    Activations Density 0.685%

    No Known Activations