© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68847
    Prev
    Next
    INDEX
    Explanations

    sql commands and keywords

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

    The neuron is looking for code identifiers or technical tokens that contain underscores.

    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
     interieur
    -1.42
    FundMe
    -1.42
     hemd
    -1.41
    蛱
    -1.38
    ———-
    -1.36
     花纹
    -1.34
    ——–
    -1.34
    錾
    -1.33
    “,
    -1.32
     situe
    -1.31
    POSITIVE LOGITS
    Although
    1.45
    It
    1.43
    While
    1.42
    Almost
    1.41
    During
    1.41
    That
    1.37
    When
    1.36
    For
    1.33
    According
    1.32
    Despite
    1.31
    Activations Density 0.053%

    No Known Activations