© 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. 34816
    Prev
    Next
    INDEX
    Explanations

    words after prepositions

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

    fifths, eighths, ninths

    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
    Mathematical
    0.42
    语
    0.38
    数学
    0.36
     stair
    0.36
     Mathematical
    0.35
     тему
    0.35
     helper
    0.35
    쑹
    0.35
     ಇದಕ್ಕೆ
    0.34
    unghi
    0.34
    POSITIVE LOGITS
     yatırım
    0.41
     proactively
    0.41
     cualquier
    0.41
     fostering
    0.40
     alguém
    0.40
     Assange
    0.39
     valorar
    0.39
     qualquer
    0.38
     instituciones
    0.38
     casually
    0.38
    Activations Density 0.002%

    No Known Activations