© 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. 242837
    Prev
    Next
    INDEX
    Explanations

    agent nouns or diminutives

    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
     ry
    0.51
     Anand
    0.49
     PluginResult
    0.48
     島
    0.47
     qí
    0.46
     Choud
    0.45
     Ahab
    0.45
    ြ
    0.45
    schutz
    0.44
     Ala
    0.44
    POSITIVE LOGITS
    '
    0.61
    Road
    0.54
    -
    0.49
    Entity
    0.48
     במש
    0.47
    One
    0.46
    விட
    0.46
    Begin
    0.45
    a
    0.45
    ל
    0.45
    Activations Density 0.001%

    No Known Activations