© 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. 100771
    Prev
    Next
    INDEX
    Explanations

    SVN subversion repository

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

    references to version control systems, particularly SVN (Subversion) and related repository management terms.

    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
    //#
    -1.34
    。”
    -1.28
    予定
    -1.27
    ″
    -1.26
     Ordens
    -1.25
     diferentes
    -1.22
     尔
    -1.22
     mengumumkan
    -1.21
    Uwagi
    -1.21
     —
    -1.21
    POSITIVE LOGITS
    狲
    1.52
    靦
    1.35
     téc
    1.34
     ит
    1.32
    緖
    1.27
    長の
    1.27
     zwłaszcza
    1.26
    ensement
    1.25
    nskap
    1.23
    羁
    1.23
    Activations Density 0.010%

    No Known Activations