© 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. 191714
    Prev
    Next
    INDEX
    Explanations

    question and answer phrases

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

    mothers holding

    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
     ҳу
    0.62
     marquées
    0.50
     дані
    0.48
     ман
    0.48
     методи
    0.48
    粓
    0.48
     энерго
    0.47
     terlihat
    0.47
     від
    0.47
     грошы
    0.46
    POSITIVE LOGITS
    :
    0.58
    ;
    0.50
     midday
    0.48
     accidents
    0.47
     heirs
    0.45
     easements
    0.44
     interplay
    0.42
     soph
    0.42
     fellowships
    0.42
     cataract
    0.41
    Activations Density 0.001%

    No Known Activations