© 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. 160132
    Prev
    Next
    INDEX
    Explanations

    from China

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

    desnuda, queen, primes, wanting

    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
    WhiteBalance
    0.51
    骓
    0.51
    azon
    0.47
    ijnlijk
    0.45
    વાડી
    0.44
    寰
    0.43
     ángulos
    0.43
    (/[
    0.43
    👀
    0.42
    JScripts
    0.42
    POSITIVE LOGITS
     but
    0.58
     to
    0.49
    鈷
    0.48
     Separation
    0.48
     rainy
    0.47
     Ease
    0.46
     ease
    0.46
     Interpreter
    0.45
     Guan
    0.45
     কিন্তু
    0.45
    Activations Density 0.004%

    No Known Activations