© 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. 180289
    Prev
    Next
    INDEX
    Explanations

    private classes

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

    advice and suggestions

    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
     Державний
    0.45
    선의
    0.43
    ຢູ່ໃນ
    0.42
    ศึกษา
    0.41
    ᚕ
    0.41
     Jacinto
    0.40
    <thead>
    0.40
     oxidative
    0.39
     انسٹ
    0.39
     adsorb
    0.38
    POSITIVE LOGITS
    с
    0.51
    lans
    0.46
    鹜
    0.46
    ج
    0.45
    et
    0.44
    or
    0.44
    ល់
    0.44
     hopelessly
    0.43
    वान
    0.42
    c
    0.42
    Activations Density 0.001%

    No Known Activations