© 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. 66302
    Prev
    Next
    INDEX
    Explanations

    Cape Westbrook, Bleeding Risk

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

    CSS padding and margin definitions in code.

    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
     version
    -1.06
     stedet
    -0.98
     postIndex
    -0.96
     to
    -0.94
     ΤΟ
    -0.91
    ύ
    -0.90
    óa
    -0.88
     uli
    -0.88
    '][]
    -0.87
     versions
    -0.87
    POSITIVE LOGITS
     nutrisi
    0.89
     jejich
    0.88
    Cin
    0.88
    Tir
    0.86
     barbati
    0.85
    können
    0.82
    Groundwater
    0.80
    Garmin
    0.80
     décédé
    0.80
    JAPAN
    0.80
    Activations Density 0.001%

    No Known Activations