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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60837
    Prev
    Next
    INDEX
    Explanations

    intervals and ranges

    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
    anneau
    -0.77
    ENODEV
    -0.74
    oa̍t
    -0.74
     ivelany
    -0.74
    offsetof
    -0.73
    codehaus
    -0.72
    Breast
    -0.70
    ográ
    -0.70
     huesos
    -0.69
    칙
    -0.69
    POSITIVE LOGITS
     interval
    2.56
     intervals
    2.25
     Interval
    2.11
    区间
    2.06
    Interval
    2.02
     range
    2.02
    interval
    1.96
    intervals
    1.91
     ranges
    1.88
     intervalo
    1.88
    Activations Density 0.047%

    No Known Activations