© 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. 34-GEMMASCOPE-RES-131K
    7. 30228
    Prev
    Next
    INDEX
    Explanations

    kidnapped, abduction, ransom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    监狱
    -0.79
     Lipo
    -0.75
     murderer
    -0.73
    spu
    -0.73
    じゅ
    -0.72
     actionPerformed
    -0.71
    狱
    -0.71
    utsu
    -0.71
    稲荷
    -0.71
    lippery
    -0.70
    POSITIVE LOGITS
     kidnapping
    4.16
     kidnapped
    3.77
     kidna
    3.66
     kidnap
    3.53
     abduction
    3.41
     abducted
    3.08
     ransom
    2.19
     Kid
    1.98
    kid
    1.95
    Kid
    1.87
    Activations Density 0.041%

    No Known Activations