© 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. 10392
    Prev
    Next
    INDEX
    Explanations

    etching process

    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
    焢
    -3.00
     medica
    -2.59
    酲
    -2.58
    Ꭳ
    -2.45
    鸲
    -2.42
    Ꮸ
    -2.39
     situa
    -2.34
     larg
    -2.28
    綃
    -2.28
     presiden
    -2.27
    POSITIVE LOGITS
    '
    3.50
    不管是
    2.45
     originalmente
    2.44
     I
    2.38
    寕
    2.22
     inicialmente
    2.08
     literalmente
    2.08
     наиболее
    2.08
     två
    2.08
     normalmente
    2.08
    Activations Density 0.006%

    No Known Activations