© 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. 44532
    Prev
    Next
    INDEX
    Explanations

    logos, WWW, chitosan composite

    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
    澌
    -2.61
    i
    -2.59
    齜
    -2.52
    o
    -2.45
    を始め
    -2.44
    
    -2.42
    滹
    -2.25
    浤
    -2.19
     they
    -2.17
    已经在
    -2.17
    POSITIVE LOGITS
     invigor
    2.63
    -
    2.56
    '
    2.42
     antiquated
    2.34
     exacting
    2.31
     ascertain
    2.28
     estekak
    2.27
     unmittelbar
    2.25
     innumerable
    2.23
     年轻
    2.19
    Activations Density 0.007%

    No Known Activations