© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111160
    Prev
    Next
    INDEX
    Explanations

    binaries and executables

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

    references to executable files or binary programs in technical documentation and code.

    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
     ''
    -1.73
     who
    -1.61
    .''
    -1.54
    。”
    -1.49
    ])){
    -1.47
    。」
    -1.46
    『
    -1.46
     one
    -1.44
    我不
    -1.43
    égi
    -1.43
    POSITIVE LOGITS
     recaudación
    1.48
     rédig
    1.43
    mployment
    1.43
     diriger
    1.40
    XXIV
    1.38
     incontr
    1.38
    XXIII
    1.38
    鲩
    1.37
     veröffentlich
    1.36
     verbinden
    1.36
    Activations Density 0.084%

    No Known Activations