© 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. 113604
    Prev
    Next
    INDEX
    Explanations

    purpose or action

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

    The neuron fires on instances of methodological descriptions—specifically on the word “used” (and its support verbs like “were used”/“was used”) in methods sections.

    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
     Inſ
    -1.84
    𐬹
    -1.73
     hatta
    -1.63
     necessidade
    -1.53
     bahkan
    -1.53
     a
    -1.52
     thậm
    -1.49
    ︲
    -1.48
     lumière
    -1.48
     Reſ
    -1.48
    POSITIVE LOGITS
     to
    2.61
     This
    2.06
     or
    1.94
     as
    1.68
     since
    1.52
     from
    1.52
     Not
    1.48
     If
    1.43
    .
    1.42
     ($
    1.40
    Activations Density 0.067%

    No Known Activations