© 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. 128961
    Prev
    Next
    INDEX
    Explanations

    discussing grade and quality

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

    The neuron is detecting numeric expressions that denote quality or grade levels (e.g. “high grade 154,” “quality 100.5,” “grade 94,” etc.).

    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
     analis
    -1.57
    hever
    -1.51
    meisters
    -1.51
    opies
    -1.45
    tiness
    -1.45
    colours
    -1.45
    consuming
    -1.43
    volent
    -1.41
    nappropriate
    -1.41
    urement
    -1.41
    POSITIVE LOGITS
    Beschrijving
    1.40
    Shortly
    1.35
     tertentu
    1.30
     gewisse
    1.27
     gelegt
    1.25
     zucchero
    1.25
     terlaris
    1.25
    地说
    1.24
     Ekonomi
    1.24
     Enkel
    1.23
    Activations Density 0.046%

    No Known Activations