© 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. 48843
    Prev
    Next
    INDEX
    Explanations

    the FIFTH CIRCUIT

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

    The neuron strongly activates on all-caps tokens such as section headings, XML/HTML tag names, or metadata labels.

    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
     what
    -1.06
     their
    -1.05
     where
    -1.05
     which
    -1.04
    Cdb
    -0.92
    ┙
    -0.86
     getting
    -0.86
    tedly
    -0.86
    縷
    -0.83
     making
    -0.82
    POSITIVE LOGITS
     chasm
    0.91
    要么
    0.91
     concom
    0.90
     tred
    0.90
     thirteenth
    0.88
     depic
    0.88
    endront
    0.87
     chameleon
    0.86
     Eleventh
    0.86
    än
    0.86
    Activations Density 0.000%

    No Known Activations