© 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. 58927
    Prev
    Next
    INDEX
    Explanations

    piece of, highest level

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

    nouns followed by descriptions

    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
     Tujuan
    0.47
     Builds
    0.45
     ಔ
    0.44
     Hosts
    0.43
    ৃত
    0.42
     Nouvelle
    0.42
     disguise
    0.41
     Workspace
    0.41
     êtres
    0.41
    대상
    0.41
    POSITIVE LOGITS
     slogans
    0.45
    гов
    0.45
    Attorney
    0.44
    𝘼
    0.44
     variances
    0.44
     infractions
    0.43
    ंसक
    0.42
    🌦
    0.42
     sano
    0.42
    छ
    0.42
    Activations Density 0.000%

    No Known Activations