© 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. 70136
    Prev
    Next
    INDEX
    Explanations

    dismissed, exception, judge

    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
    ющий
    -0.66
     From
    -0.65
     iš
    -0.64
    емых
    -0.63
     电脑
    -0.62
    ственный
    -0.61
     FROM
    -0.60
    immunity
    -0.60
     咲
    -0.60
     İç
    -0.60
    POSITIVE LOGITS
     elastic
    0.71
     Format
    0.71
    onesa
    0.69
     отца
    0.69
     دقيقة
    0.66
    usec
    0.66
    utveck
    0.65
    azah
    0.64
     vors
    0.64
    ବ
    0.63
    Activations Density 0.097%

    No Known Activations