© 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. 109729
    Prev
    Next
    INDEX
    Explanations

    within a duration

    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
    MANY
    -0.82
    ist
    -0.79
    şen
    -0.77
    ウド
    -0.75
    多的
    -0.75
     Loo
    -0.75
    ถึง
    -0.74
    tsc
    -0.72
     قاعدة
    -0.72
    vid
    -0.72
    POSITIVE LOGITS
     minutes
    2.13
     seconds
    1.94
     days
    1.91
     months
    1.89
     weeks
    1.86
     moments
    1.78
     hours
    1.70
     years
    1.38
    minutes
    1.37
     semanas
    1.35
    Activations Density 0.027%

    No Known Activations