© 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. 232557
    Prev
    Next
    INDEX
    Explanations

    verbs followed by nouns

    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
    訓
    0.49
    вають
    0.46
    Nearly
    0.46
    把握
    0.45
    ాతం
    0.45
    AssetDiscovery
    0.44
    IDAD
    0.44
    astien
    0.44
    졍
    0.44
    ानंतर
    0.43
    POSITIVE LOGITS
     our
    0.54
    followers
    0.54
    nail
    0.50
     joystick
    0.50
    locals
    0.50
     Fuj
    0.49
     figurine
    0.49
     bangs
    0.49
     Uy
    0.49
     ephemeral
    0.48
    Activations Density 0.000%

    No Known Activations