© 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. 113129
    Prev
    Next
    INDEX
    Explanations

    clauses starting with certain words

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

    meaning so much

    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
    喺
    0.54
     messo
    0.49
     семи
    0.44
     почему
    0.43
     ウェ
    0.43
     вось
    0.43
     ನಾನು
    0.43
     wyposaż
    0.43
     حیر
    0.43
     वेब
    0.42
    POSITIVE LOGITS
    ãi
    0.42
     fast
    0.39
    弊
    0.38
    രി
    0.38
    äude
    0.38
    yr
    0.38
     scald
    0.37
     rate
    0.37
    活跃
    0.36
    циа
    0.36
    Activations Density 0.000%

    No Known Activations