© 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. 164932
    Prev
    Next
    INDEX
    Explanations

    conservative government

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

    invasion, less connected, training program, Sicily

    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
    ab
    0.54
    re
    0.52
    k
    0.52
     own
    0.50
     Pretty
    0.50
    rv
    0.50
    ek
    0.48
    g
    0.48
    cb
    0.47
     haircuts
    0.46
    POSITIVE LOGITS
    嫘
    0.53
    Conf
    0.51
    Cabinet
    0.50
    ຂໍ້ມ
    0.47
    Arist
    0.46
    Arithmetic
    0.46
    Bamboo
    0.44
    ☯
    0.44
    骥
    0.44
    六
    0.44
    Activations Density 0.004%

    No Known Activations