© 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. 111571
    Prev
    Next
    INDEX
    Explanations

    from cqlengine, stator, Xamarin

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

    digits in numeric sequences, especially in code identifiers, citations, and version numbers.

    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
    Numerous
    -1.74
     innumerable
    -1.70
     their
    -1.66
    是非常
    -1.66
     Numerous
    -1.63
     during
    -1.58
     nearing
    -1.58
     on
    -1.55
    Many
    -1.54
     at
    -1.53
    POSITIVE LOGITS
    contrar
    1.77
    憷
    1.68
    
    1.66
    轳
    1.66
    itisation
    1.64
     bolsillos
    1.59
    ↵↵
    1.57
     zoude
    1.57
    ⢫
    1.55
    celotti
    1.54
    Activations Density 0.001%

    No Known Activations