© 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. 221998
    Prev
    Next
    INDEX
    Explanations

    foreign language or specialized terms

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

    original creations

    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
    bindingFields
    0.47
    getZoom
    0.45
    gramModel
    0.45
    ྃ
    0.44
     bicovariant
    0.44
     discerned
    0.43
     удовлетво
    0.43
    örper
    0.42
     большую
    0.42
    ahankan
    0.42
    POSITIVE LOGITS
    EV
    0.54
    IE
    0.53
    GA
    0.52
    Direct
    0.52
    CNN
    0.52
    対象
    0.51
     DIRECT
    0.50
    SHARE
    0.50
    軽
    0.50
     Creation
    0.49
    Activations Density 0.001%

    No Known Activations