© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59753
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    ği
    -0.72
    ∝
    -0.71
     BLO
    -0.71
     hinders
    -0.68
     Bloch
    -0.68
    Invo
    -0.67
    ooka
    -0.66
    ager
    -0.65
    ด้าน
    -0.65
     '',
    
    -0.65
    POSITIVE LOGITS
    ㊙
    0.70
     disinfect
    0.67
    Retrieval
    0.67
    getHeader
    0.66
     動物
    0.65
    poses
    0.65
     математи
    0.65
    ป
    0.64
     muslin
    0.63
    setMinimum
    0.62
    Activations Density 0.097%

    No Known Activations