© 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. 20985
    Prev
    Next
    INDEX
    Explanations

    conjunctions and clause connectors

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

    Edison demonstrates, already well-off, today Sunday

    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
     bespoke
    0.64
     revital
    0.57
     shortfall
    0.57
    퀄
    0.56
     devait
    0.54
     operated
    0.54
     finanz
    0.53
     revamped
    0.53
     multidiscipl
    0.52
     underpinned
    0.52
    POSITIVE LOGITS
     Когда
    0.58
    หรือ
    0.55
     あなた
    0.55
    ແລະ
    0.54
    しながら
    0.50
     ぐらい
    0.50
     Và
    0.50
     ו
    0.49
    และ
    0.49
     голове
    0.49
    Activations Density 0.000%

    No Known Activations