© 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. 34-GEMMASCOPE-RES-131K
    7. 107880
    Prev
    Next
    INDEX
    Explanations

    code comments or questions

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

    The neuron fires strongly on the boilerplate comment and license‐header blocks (e.g. the leading “//” lines and copyright/license metadata) in source code files.

    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
     Fürst
    -0.81
     traceability
    -0.81
     Hora
    -0.78
     narcotic
    -0.74
     respeto
    -0.73
    彼が
    -0.72
     Lambeth
    -0.72
     doped
    -0.72
    靥
    -0.71
     amazed
    -0.71
    POSITIVE LOGITS
     vit
    0.85
     Vit
    0.82
    øb
    0.82
    angelog
    0.80
     meni
    0.77
    roach
    0.77
     Caesar
    0.76
     koke
    0.76
     Experimental
    0.75
    Symptoms
    0.73
    Activations Density 0.008%

    No Known Activations