© 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. 133573
    Prev
    Next
    INDEX
    Explanations

    places, things, concepts

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

    mother, sweetheart, or sweetheart

    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
    setDate
    0.48
    ార్
    0.46
    と比較
    0.45
    ಲ್ಯಾ
    0.44
     ಮಕ್ಕ
    0.44
    ᱕
    0.44
    球迷
    0.43
    acuse
    0.43
    
    0.43
    queda
    0.43
    POSITIVE LOGITS
     rohk
    0.44
    ЛИ
    0.44
     exercer
    0.44
     produt
    0.43
     conçu
    0.43
     egent
    0.43
     eigent
    0.42
     destinés
    0.42
     disk
    0.41
     opportunities
    0.41
    Activations Density 0.001%

    No Known Activations