© 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. 109708
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     undercut
    -1.15
     undermined
    -0.98
     undermine
    -0.97
     undermining
    -0.92
     weaken
    -0.90
     Under
    -0.90
    无可
    -0.79
    under
    -0.77
    ঈ
    -0.76
     weakens
    -0.75
    POSITIVE LOGITS
    霾
    0.74
     bå
    0.74
    Sq
    0.71
     Discrimination
    0.69
     hic
    0.69
     loneliness
    0.68
     discrimination
    0.68
    臧
    0.68
     prevenir
    0.66
     visitor
    0.66
    Activations Density 0.043%

    No Known Activations