© 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. 31276
    Prev
    Next
    INDEX
    Explanations

    numbers after semicolon

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

    The neuron is chiefly detecting numeric tokens in reference citations—e.g. volume numbers, years, page numbers, and other digit sequences.

    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
     particularly
    -0.90
    لاج
    -0.89
     especially
    -0.89
     like
    -0.88
     it
    -0.87
     around
    -0.82
     reckless
    -0.82
     дитя
    -0.81
    قدام
    -0.81
     almost
    -0.81
    POSITIVE LOGITS
     釣り
    0.95
    悻
    0.90
    ्ष
    0.90
     кле
    0.89
    órias
    0.87
     https
    0.87
     amie
    0.85
    𝑗
    0.84
     éclairage
    0.83
    umbe
    0.82
    Activations Density 0.049%

    No Known Activations