© 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. 10-GEMMASCOPE-RES-131K
    7. 21450
    Prev
    Next
    INDEX
    Explanations

    misconceptions and convex optimization

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

    The neuron fires on tokens containing the substring “con,” e.g. words like “misconceptions,” “miscon,” and “convex.”

    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
     Она
    -2.73
     Даже
    -2.36
     älteren
    -2.31
    瑧
    -2.23
     Ее
    -2.22
     És
    -2.22
     neuen
    -2.13
     ask
    -2.11
     classify
    -2.09
    </b>
    -2.08
    POSITIVE LOGITS
    s
    2.70
    "
    2.61
    ing
    2.56
    ness
    2.30
     للاس
    2.27
    g
    2.23
    橚
    2.19
     mengaku
    2.17
     iſt
    2.13
    ็
    2.13
    Activations Density 0.003%

    No Known Activations