© 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. 48712
    Prev
    Next
    INDEX
    Explanations

    preposition followed by diverse entities

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

    list items followed by common words

    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
    łoś
    0.49
     поведения
    0.48
     разгово
    0.48
    angering
    0.48
     бло
    0.47
     놀
    0.47
    новен
    0.47
    播出
    0.46
     кварти
    0.46
     ಮನೆಯ
    0.46
    POSITIVE LOGITS
    '
    0.56
    S
    0.52
     previsto
    0.49
    I
    0.48
    *
    0.47
    الصف
    0.47
     fase
    0.46
     cult
    0.46
    _(
    0.46
    С
    0.45
    Activations Density 0.002%

    No Known Activations