© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109928
    Prev
    Next
    INDEX
    Explanations

    crime offending routine offender

    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
     Favre
    -0.88
    remes
    -0.81
     attiv
    -0.80
     Olin
    -0.79
    слу
    -0.77
    MARIA
    -0.77
     کاب
    -0.77
     парфю
    -0.77
    améliorer
    -0.76
     TUB
    -0.76
    POSITIVE LOGITS
     crimin
    1.14
     Routine
    1.07
    Criminal
    1.05
     offending
    1.02
     Criminal
    1.02
    Routine
    0.99
     Crime
    0.99
     crime
    0.98
    Crime
    0.98
     offender
    0.97
    Activations Density 0.035%

    No Known Activations