© 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. 22-GEMMASCOPE-RES-131K
    7. 34569
    Prev
    Next
    INDEX
    Explanations

    sentence separators and punctuation

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

    The neuron strongly activates on standalone multi‐digit numeric strings (e.g. page or section 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_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
    ᳝
    -2.13
    翾
    -2.09
    涐
    -1.98
     theor
    -1.98
     textBox
    -1.95
    晅
    -1.93
     庭
    -1.91
    天神
    -1.90
    😈
    -1.89
    鳢
    -1.89
    POSITIVE LOGITS
    The
    3.09
    s
    2.41
    一个
    2.06
    ]
    2.06
    有很多
    2.05
    整个
    2.03
    It
    2.00
     一
    1.95
     linken
    1.95
    有着
    1.94
    Activations Density 0.015%

    No Known Activations