© 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. 42106
    Prev
    Next
    INDEX
    Explanations

    Novartis, concerts, and all

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

    Cape Town, combustion sustains, ruby, Rice, maximizes, spark

    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
    мум
    0.51
    чни
    0.50
     Shaikh
    0.50
     Públic
    0.47
     pripad
    0.47
     गट
    0.46
    যেন
    0.46
    
    0.45
    웬
    0.45
     동일
    0.44
    POSITIVE LOGITS
     કર્યા
    0.47
     علاج
    0.46
    ہ
    0.44
    ↓↓
    0.44
    lh
    0.43
     registrado
    0.43
    URY
    0.42
    maintenance
    0.42
     ビ
    0.42
    について
    0.41
    Activations Density 0.001%

    No Known Activations