© 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. 103512
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and brackets

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

    closing parentheses in transcripts, code, or structured text formatting.

    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
     "
    -2.34
     -"
    -1.75
    “
    -1.71
     need
    -1.66
    c
    -1.58
    ."
    -1.48
    0
    -1.47
     '
    -1.46
     -
    -1.44
     męska
    -1.41
    POSITIVE LOGITS
     siff
    1.61
     brill
    1.60
     fondu
    1.57
     diamant
    1.54
     maxime
    1.51
    راعة
    1.48
     oogen
    1.43
    उत्तर
    1.42
     palma
    1.40
     alamu
    1.39
    Activations Density 0.002%

    No Known Activations