© 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. 137949
    Prev
    Next
    INDEX
    Explanations

    Saint Leo, FL and Jesus

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

    related to words ending in ing

    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
     adjourn
    0.56
    জ
    0.54
    ސ
    0.46
    Feel
    0.46
    ㄑ
    0.46
    BOOL
    0.45
    პ
    0.45
    チョ
    0.44
    ページ
    0.44
    ロッ
    0.44
    POSITIVE LOGITS
    aking
    0.55
    ying
    0.50
    izens
    0.49
    izen
    0.49
     Byzantine
    0.48
    itur
    0.47
    anking
    0.47
    aken
    0.46
    anak
    0.46
     ง
    0.46
    Activations Density 0.000%

    No Known Activations