© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113897
    Prev
    Next
    INDEX
    Explanations

    unauthorized access or unsupported

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

    the word "unauthorized" in technical or security-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     But
    -2.47
     เมื่อ
    -2.44
     cuando
    -2.36
    re
    -2.14
     แต่
    -2.13
     {
    -2.13
     When
    -2.09
     The
    -2.06
     ketika
    -1.96
    ebab
    -1.96
    POSITIVE LOGITS
    .
    3.55
    酲
    2.67
    其妙
    2.47
    the
    2.28
     był
    2.27
    thétique
    2.20
    ᠂
    2.19
    歺
    2.19
    之事
    2.17
    ༔
    2.14
    Activations Density 0.002%

    No Known Activations