© 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. 92120
    Prev
    Next
    INDEX
    Explanations

    next post

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

    possessives or common phrases

    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
    ぽ
    0.45
    Subset
    0.44
    活躍
    0.44
    زم
    0.43
     ਹੈ
    0.43
    धव
    0.43
    ب
    0.43
    ک
    0.42
    ภาย
    0.42
    (";
    0.42
    POSITIVE LOGITS
     outta
    0.50
     trampled
    0.50
     falsely
    0.49
     bellow
    0.49
     manly
    0.49
     suche
    0.48
     crammed
    0.48
     hurriedly
    0.47
     rusting
    0.47
     homely
    0.46
    Activations Density 0.000%

    No Known Activations