© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123621
    Prev
    Next
    INDEX
    Explanations

    daily updates or ongoing content

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

    descriptive noun phrases

    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
    Negative Logits
     Plumbing
    0.46
     éché
    0.45
    Typically
    0.45
    騫
    0.44
     typically
    0.44
     phasing
    0.44
     fusible
    0.43
     chi
    0.43
     Chicago
    0.42
     Chorus
    0.42
    POSITIVE LOGITS
    лів
    0.44
    ulie
    0.44
     партия
    0.43
    izar
    0.41
    蔘
    0.41
    alkeeper
    0.41
    urs
    0.39
    butanol
    0.39
    wang
    0.39
    pulsewidth
    0.39
    Activations Density 0.001%

    No Known Activations