© 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. 34-GEMMASCOPE-RES-131K
    7. 57829
    Prev
    Next
    INDEX
    Explanations

    URLs and code strings

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

    The neuron activates on tokens that are numeric or contain digit sequences (e.g. version numbers, IDs, hex strings, or plain 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_34/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
    ),
    -2.17
    %),
    -1.77
    .),
    -1.72
     ),
    -1.60
    ?),
    -1.59
    )$,
    -1.55
     Перейти
    -1.49
    ...),
    -1.47
    ),
    -1.42
    ()),
    -1.42
    POSITIVE LOGITS
    "
    3.06
    」
    2.45
    '
    2.27
    ”
    1.98
    """
    1.82
    "
    1.80
    }"
    1.69
    ()
    1.68
    []"
    1.61
    »
    1.59
    Activations Density 0.071%

    No Known Activations