© 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. 22-GEMMASCOPE-RES-131K
    7. 73406
    Prev
    Next
    INDEX
    Explanations

    code keywords and identifiers

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

    The neuron fires on programming identifiers made of multiple concatenated words (e.g. CamelCase or multi‐word names).

    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
     and
    -2.63
    を目指す
    -1.55
     concentrado
    -1.50
    Ẩ
    -1.50
    はコチラ
    -1.49
    Ừ
    -1.49
    raujo
    -1.48
    に使用
    -1.46
     condicionado
    -1.45
     plataformas
    -1.45
    POSITIVE LOGITS
    <bos>
    1.95
    說道
    1.50
    ss
    1.46
    这也
    1.38
    l
    1.37
    w
    1.36
    c
    1.35
    搅拌
    1.35
    le
    1.31
    んでも
    1.30
    Activations Density 0.013%

    No Known Activations