© 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. 101203
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

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

    periods or dots in code, technical documentation, and structured text formats.

    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
     all
    -1.91
     not
    -1.63
     any
    -1.59
    mamp
    -1.58
     with
    -1.52
     a
    -1.52
     even
    -1.48
     before
    -1.48
    ｫ
    -1.47
     which
    -1.42
    POSITIVE LOGITS
    鸲
    1.80
    etc
    1.80
    ſſen
    1.70
    ：“……”
    1.66
    更好的
    1.55
    が付
    1.55
    h
    1.49
    amples
    1.49
    aren
    1.48
     tersebut
    1.46
    Activations Density 0.147%

    No Known Activations