© 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. 84216
    Prev
    Next
    INDEX
    Explanations

    proper nouns and institutions

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

    company and university affiliations

    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
     พวก
    0.44
    饶
    0.40
     dragState
    0.39
     liturgical
    0.39
     Shader
    0.38
     boosters
    0.38
    谶
    0.38
     ótimo
    0.37
     Parch
    0.36
    StarGo
    0.36
    POSITIVE LOGITS
     University
    0.46
    kule
    0.45
    cluse
    0.45
    University
    0.44
     Department
    0.43
    Institut
    0.43
     ${
    0.43
    address
    0.42
    Institute
    0.42
    ium
    0.42
    Activations Density 0.034%

    No Known Activations