© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68313
    Prev
    Next
    INDEX
    Explanations

    speeches and addresses

    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
    ”
    -2.48
    朦
    -2.39
     –
    -2.33
     ваше
    -2.33
     “
    -2.28
    –
    -2.22
    同伴
    -2.20
    挑戦
    -2.20
     
    -2.20
     Hinblick
    -2.17
    POSITIVE LOGITS
    鏷
    2.78
    
    2.75
    嫗
    2.66
     giapponese
    2.63
     فنا
    2.59
     ぽ
    2.58
    谡
    2.58
    筚
    2.55
     pering
    2.52
    y
    2.52
    Activations Density 0.006%

    No Known Activations