© 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. 231821
    Prev
    Next
    INDEX
    Explanations

    common law

    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
    敔
    0.54
    上記
    0.52
    持續
    0.51
    )}^{\
    0.51
     ஆயிர
    0.50
    設計
    0.49
    毎年
    0.49
    ंडीगढ़
    0.48
     individuais
    0.48
    各地
    0.48
    POSITIVE LOGITS
     intricate
    0.47
    ”
    0.45
     watered
    0.44
     cracks
    0.44
     cracked
    0.44
     adjacent
    0.43
     loved
    0.43
     intuitive
    0.43
     surprises
    0.42
     watery
    0.42
    Activations Density 0.000%

    No Known Activations