© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72458
    Prev
    Next
    INDEX
    Explanations

    documentation comments and tags

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

    This neuron specializes in spotting code documentation markers and tags (e.g. XML/attribute-style “devdoc” and “doc=” annotations).

    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
     you
    -1.84
     barata
    -1.69
    %;
    -1.53
     its
    -1.52
    lxt
    -1.50
     sabias
    -1.50
    亿元
    -1.48
     Hinblick
    -1.47
     estampada
    -1.47
     hermosas
    -1.47
    POSITIVE LOGITS
    8
    1.91
    0
    1.60
    z
    1.54
    lichkeiten
    1.53
     barnet
    1.52
    j
    1.50
    躋
    1.49
    w
    1.47
     jule
    1.46
     abomination
    1.46
    Activations Density 0.000%

    No Known Activations