© 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. 149526
    Prev
    Next
    INDEX
    Explanations

    verified, network, factors, separate, suddenly, attacked

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

    Sherbrooke St. West addresses

    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
     نیست
    0.55
     europeo
    0.54
     européen
    0.54
    샨
    0.53
     토
    0.52
     сексуа
    0.52
    ида
    0.52
    ۳
    0.52
     решения
    0.51
     tony
    0.51
    POSITIVE LOGITS
    Q
    0.49
    Gem
    0.48
    ERROR
    0.48
    Giovanni
    0.47
    Fitness
    0.46
    is
    0.45
    ao
    0.44
    TARGET
    0.44
    Ka
    0.43
    on
    0.43
    Activations Density 0.002%

    No Known Activations