© 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. 112813
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code

    np_acts-logits-general · gemini-2.5-flash-lite

    bullet points (asterisks) in software license text, particularly in BSD-style licenses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    "
    -1.91
    He
    -1.70
    In
    -1.69
    e
    -1.68
     for
    -1.67
     just
    -1.66
     then
    -1.65
    ?
    -1.63
    Just
    -1.61
     He
    -1.52
    POSITIVE LOGITS
    iciais
    1.84
    ritis
    1.73
    嫗
    1.70
     raiſ
    1.65
    
    1.63
     合集
    1.62
    ༔
    1.59
    
    1.59
    tijd
    1.58
    」,
    1.55
    Activations Density 0.070%

    No Known Activations