© 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. 117893
    Prev
    Next
    INDEX
    Explanations

    rights to

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

    comparisons and consequences

    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
    ラ
    0.50
     interdit
    0.49
    radi
    0.47
    ግ
    0.46
    प
    0.46
     magnetic
    0.46
     chirurg
    0.45
    radio
    0.44
    b
    0.43
    Η
    0.43
    POSITIVE LOGITS
     Nowadays
    0.47
     Warszawie
    0.47
    在这里
    0.47
     Đó
    0.46
     These
    0.46
     Funding
    0.46
     Literature
    0.46
     Initiative
    0.46
     Those
    0.45
     السنوات
    0.45
    Activations Density 0.000%

    No Known Activations