© 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. 10-GEMMASCOPE-RES-131K
    7. 103190
    Prev
    Next
    INDEX
    Explanations

    mathematical questions solved followed by selection

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

    This neuron responds strongly to standalone punctuation marks (especially “?” and “.”) and isolated digits used as list or question markers.

    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
    mucha
    -1.14
    pewa
    -1.13
    Cinta
    -1.12
    ticion
    -1.11
     fön
    -1.09
     öl
    -1.05
     řekl
    -1.05
     diinginkan
    -1.05
     apellidos
    -1.05
    воря
    -1.03
    POSITIVE LOGITS
     there
    1.35
     pinulongan
    1.32
    ológica
    1.30
     its
    1.28
     있다
    1.27
    犼
    1.27
    因为它
    1.26
     arduous
    1.25
     coś
    1.23
     whims
    1.22
    Activations Density 0.126%

    No Known Activations