© 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. 104631
    Prev
    Next
    INDEX
    Explanations

    common command-line options

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

    command-line options and flags in technical documentation, particularly those preceded by dashes or hyphens.

    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
    豨
    -1.76
    癭
    -1.52
    alers
    -1.46
    🚘
    -1.43
     ieg
    -1.41
     GETS
    -1.40
     proie
    -1.39
    ✏
    -1.39
     BOARD
    -1.38
    lamabad
    -1.38
    POSITIVE LOGITS
    8
    2.17
    4
    2.17
    1
    1.93
    9
    1.86
     "
    1.84
    6
    1.83
    3
    1.73
    7
    1.73
    0
    1.73
    5
    1.71
    Activations Density 0.004%

    No Known Activations