© 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. 142673
    Prev
    Next
    INDEX
    Explanations

    specific entities and languages

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

    break down `both` `mold` `platforms`

    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
     application
    0.55
     orifice
    0.52
    e
    0.52
    ability
    0.47
     water
    0.47
     emulsion
    0.47
    em
    0.47
     bottles
    0.46
    or
    0.46
    IS
    0.46
    POSITIVE LOGITS
    邙
    0.54
    вається
    0.48
     σχετικά
    0.48
     दिले
    0.47
    驕
    0.47
     गुंतवणूक
    0.46
     téléphone
    0.46
    集團
    0.46
    ̀nh
    0.45
    呯
    0.45
    Activations Density 0.000%

    No Known Activations