© 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. 125231
    Prev
    Next
    INDEX
    Explanations

    information pertaining, Molding Experts, California gubernatorial

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

    arranged marriage

    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
    ῴ
    0.45
    ochemistry
    0.45
    ully
    0.44
     Siempre
    0.43
     धमाकेदार
    0.43
    odu
    0.42
    ativa
    0.42
    emia
    0.42
    golang
    0.41
    kval
    0.41
    POSITIVE LOGITS
    湫
    0.46
    క్ర
    0.45
     зелены
    0.44
    ཥ
    0.44
    🕘
    0.43
    십
    0.43
    ഢ
    0.43
    Ǘ
    0.42
     cheat
    0.42
    នឹង
    0.42
    Activations Density 0.001%

    No Known Activations