© 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. 118705
    Prev
    Next
    INDEX
    Explanations

    Rod Rosenstein indictments

    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
    깥
    -0.81
    
    -0.77
    physiology
    -0.73
    Result
    -0.72
    생
    -0.70
     Apostle
    -0.70
    equiv
    -0.70
     Negeri
    -0.69
    ifers
    -0.69
     احت
    -0.69
    POSITIVE LOGITS
    Brunswick
    0.82
     indicted
    0.82
     Farina
    0.81
     Guilty
    0.81
     Mana
    0.81
     perjury
    0.79
    Mana
    0.79
     Surrender
    0.77
    Guilty
    0.76
     Dulles
    0.75
    Activations Density 0.012%

    No Known Activations