© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72727
    Prev
    Next
    INDEX
    Explanations

    operation and management

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

    technical functions and code

    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
    Negative Logits
    谈判
    0.46
    smallest
    0.44
    ro
    0.44
    ph
    0.44
    7
    0.43
    ussions
    0.42
    вез
    0.42
    maven
    0.42
    肌
    0.42
    ll
    0.41
    POSITIVE LOGITS
     bindings
    0.50
     wrestled
    0.49
    DEBUGFS
    0.48
    ামিন
    0.48
    ′-
    0.47
    ালিক
    0.47
     albums
    0.46
    áneamente
    0.46
     uš
    0.46
     registries
    0.45
    Activations Density 0.000%

    No Known Activations