© 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. 22-GEMMASCOPE-RES-131K
    7. 14041
    Prev
    Next
    INDEX
    Explanations

    human subjects

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

    lists, numbers, or statistics in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    bise
    -1.01
     alfo
    -0.91
     minum
    -0.90
    jshint
    -0.88
    IFFS
    -0.88
     iran
    -0.88
     carlos
    -0.88
     perasaan
    -0.86
     nowa
    -0.85
     définitivement
    -0.84
    POSITIVE LOGITS
    Occasionally
    1.36
     occasional
    1.28
     limited
    1.15
     certain
    1.15
    بعض
    1.12
     algunos
    1.09
     некоторых
    1.09
    บาง
    1.09
    However
    1.07
     occasionally
    1.07
    Activations Density 0.141%

    No Known Activations