© 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. 134095
    Prev
    Next
    INDEX
    Explanations

    real estate team

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

    don't expect me to coddle

    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
    B
    0.52
    T
    0.50
    F
    0.47
    衛
    0.47
     AN
    0.46
    獲
    0.45
    S
    0.44
    D
    0.44
    H
    0.44
     It
    0.44
    POSITIVE LOGITS
     Альбер
    0.50
    ccgi
    0.46
    িবাস
    0.45
    phenylsulfanyl
    0.44
    все
    0.44
     Köln
    0.44
    skoj
    0.44
    dayspecial
    0.44
    reportBody
    0.44
     amerikan
    0.43
    Activations Density 0.001%

    No Known Activations