© 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. 16817
    Prev
    Next
    INDEX
    Explanations

    management and services

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

    process automation, language models

    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
    :
    0.62
    it
    0.53
    8
    0.53
    ii
    0.48
    ai
    0.47
    ė
    0.45
     .
    0.44
    os
    0.43
    and
    0.43
    2
    0.42
    POSITIVE LOGITS
     ചില
    0.54
     这些
    0.51
     Những
    0.50
     කො
    0.46
     そんな
    0.44
     නිෂ්පා
    0.43
     scaleOf
    0.43
     mouve
    0.43
     ද
    0.42
    พ
    0.42
    Activations Density 0.243%

    No Known Activations