© 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. 99372
    Prev
    Next
    INDEX
    Explanations

    CB followed by numbers or letters

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

    The neuron activates on occurrences of the prefix “CB” in alphanumeric compound or model identifiers.

    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
    但我
    -2.52
     That
    -2.47
     Previously
    -2.23
    ⚣
    -2.23
    牍
    -2.22
     Typical
    -2.17
    
    -2.16
     "${
    -2.16
    并在
    -2.14
    ي
    -2.13
    POSITIVE LOGITS
    k
    3.06
    s
    3.06
    \
    2.88
    "
    2.84
    <
    2.66
    ",
    2.59
    真的
    2.58
     blumen
    2.39
    '
    2.39
    am
    2.30
    Activations Density 0.004%

    No Known Activations