© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67964
    Prev
    Next
    INDEX
    Explanations

    Oops

    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
    0
    -3.22
     stehenden
    -2.91
    3
    -2.78
     vollständ
    -2.72
     preexisting
    -2.69
     enormous
    -2.67
     erwähnten
    -2.63
    狆
    -2.59
     formidable
    -2.58
     białe
    -2.58
    POSITIVE LOGITS
    蹰
    3.05
    籥
    2.81
    鼱
    2.67
     promove
    2.63
     dies
    2.47
    y
    2.44
     auch
    2.36
     planific
    2.36
     documentos
    2.34
     desblo
    2.33
    Activations Density 0.001%

    No Known Activations