© 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. 111977
    Prev
    Next
    INDEX
    Explanations

    sum calculation

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

    This neuron fires on numeric expressions and related summation terms (e.g. “sum,” “SUM,” or literal numbers).

    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
     -----
    -1.47
    eps
    -1.39
    ligente
    -1.37
    ";
    -1.36
     rn
    -1.35
     ........
    -1.34
    VERY
    -1.34
    ..........
    -1.34
     ";
    -1.32
     Tentang
    -1.32
    POSITIVE LOGITS
    ,
    1.49
     äls
    1.45
     médic
    1.41
    รู้สึก
    1.41
     alleviate
    1.40
     subida
    1.39
     fiables
    1.39
     övers
    1.35
     says
    1.34
     cherchés
    1.34
    Activations Density 0.077%

    No Known Activations