© 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. 197085
    Prev
    Next
    INDEX
    Explanations

    server running

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

    guesthouse search queries

    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
    aturing
    0.49
     বিবেচনায়
    0.45
     Intelligence
    0.45
    考虑到
    0.44
    imentary
    0.44
     इंटेलिज
    0.44
    🐎
    0.44
    考虑
    0.44
     কাজের
    0.43
    IMENT
    0.43
    POSITIVE LOGITS
     Brot
    0.51
    ু
    0.49
     Генера
    0.47
     beetles
    0.47
     invertebr
    0.47
     сервер
    0.47
     pept
    0.47
     MUST
    0.46
    мени
    0.46
     removable
    0.46
    Activations Density 0.001%

    No Known Activations