© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25699
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

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

    The neuron fires on high-level mathematical result phrases—words like “derive,” “expression,” “formula,” “analytical,” or “recursion relations” that announce key theoretical results.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -1.38
    atzes
    -1.34
    cić
    -1.28
     الحكومة
    -1.20
    kurse
    -1.19
    strö
    -1.19
     Unterscheidung
    -1.18
    蘩
    -1.18
     issus
    -1.17
     quelques
    -1.16
    POSITIVE LOGITS
     for
    2.70
     their
    1.88
     of
    1.78
     which
    1.75
     that
    1.70
     from
    1.42
     like
    1.36
     about
    1.30
     now
    1.28
     everyone
    1.28
    Activations Density 0.036%

    No Known Activations