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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129683
    Prev
    Next
    INDEX
    Explanations

    words starting with pri

    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_10/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
    ↵↵
    -3.92
     “
    -3.31
    “
    -2.92
     we
    -2.66
    (“
    -2.45
    薷
    -2.45
     surpassing
    -2.44
    <bos>
    -2.41
     gewöhnlich
    -2.38
     […]
    -2.33
    POSITIVE LOGITS
    聍
    3.23
    だわ
    2.92
    琿
    2.89
     humeur
    2.75
    鄚
    2.73
     所以
    2.69
    祘
    2.63
    หรือ
    2.61
    
    2.61
     händer
    2.56
    Activations Density 0.004%

    No Known Activations