© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103112
    Prev
    Next
    INDEX
    Explanations

    documentation \alias usage

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

    backslash commands in LaTeX or code documentation (e.g., \alias, \author, \usage, \title).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on backslashes that introduce markup or macro commands (e.g. “\alias”, “\author”, “\title”, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ’
    -1.95
    </h3>
    -1.92
     angebra
    -1.77
    を使用した
    -1.76
    ほしい
    -1.76
     perú
    -1.71
     jopa
    -1.70
    Après
    -1.66
    囹
    -1.64
     übri
    -1.63
    POSITIVE LOGITS
     to
    2.30
    t
    1.92
    .*")]
    1.91
     be
    1.84
     )}
    1.82
    煦
    1.81
    谘
    1.78
     JSONException
    1.74
    =}
    1.73
     mouseY
    1.71
    Activations Density 0.000%

    No Known Activations