© 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. 132733
    Prev
    Next
    INDEX
    Explanations

    verbs followed by actions

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

    all language concepts

    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
    UTC
    0.59
    DATE
    0.52
    ISH
    0.50
    <0x80>
    0.50
     an
    0.50
     DATE
    0.49
    சர
    0.49
    IRA
    0.47
    י
    0.47
    णा
    0.46
    POSITIVE LOGITS
     benutzen
    0.55
     Reinigung
    0.50
     марки
    0.50
     wobei
    0.50
    !..
    0.50
     قي
    0.49
    юнча
    0.48
     افت
    0.48
    jede
    0.48
     ملك
    0.47
    Activations Density 0.000%

    No Known Activations