© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93441
    Prev
    Next
    INDEX
    Explanations

    JSDoc code documentation keywords

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

    The neuron fires on documentation-tag annotations (e.g. JSDoc/PhpDoc “@…” tags) in comment blocks.

    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
     bijzondere
    -1.45
     ständig
    -1.42
     apoio
    -1.30
     tevens
    -1.30
     eenvou
    -1.28
     vriende
    -1.27
     arbeitet
    -1.26
     konzent
    -1.26
     meestal
    -1.23
     fijne
    -1.23
    POSITIVE LOGITS
    </b>
    1.60
     in
    1.55
    	
    1.38
         
    1.36
     with
    1.34
     so
    1.34
    !!
    1.34
    1.34
    </strong>
    1.32
     oktober
    1.31
    Activations Density 0.031%

    No Known Activations