© 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. 128003
    Prev
    Next
    INDEX
    Explanations

    evidence, theme, stories, bonus, environment

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

    preposition or determiner followed by a noun

    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
    ậy
    0.48
    지로
    0.47
    lash
    0.47
    べく
    0.46
    ştik
    0.46
    rization
    0.46
    ょう
    0.45
    명
    0.44
     라고
    0.44
     Katha
    0.43
    POSITIVE LOGITS
     Stratford
    0.45
    ,,
    0.43
     দেবতার
    0.43
     STI
    0.43
     Performs
    0.43
     elles
    0.41
    >>,
    0.41
     Connection
    0.41
     Eureka
    0.40
     प्रणाम
    0.40
    Activations Density 0.001%

    No Known Activations