© 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. 34-GEMMASCOPE-RES-131K
    7. 65212
    Prev
    Next
    INDEX
    Explanations

    Vascular function, Impact of

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

    escape characters in programming code, particularly backslash sequences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting backslash‐initiated escape sequences and regex character‐escaping patterns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    neutral
    -0.78
     mezi
    -0.77
    攢
    -0.77
    📪
    -0.76
    lico
    -0.76
     zanah
    -0.74
     Versicher
    -0.73
     espectadores
    -0.71
    alian
    -0.70
    滿足
    -0.70
    POSITIVE LOGITS
     Epis
    0.83
    uffff
    0.78
    letion
    0.78
     domic
    0.77
    κι
    0.75
    NewGuid
    0.75
     octopus
    0.73
    avanje
    0.73
     fiduciary
    0.73
     Octopus
    0.72
    Activations Density 0.007%

    No Known Activations