© 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. 45267
    Prev
    Next
    INDEX
    Explanations

    informing or warning

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

    The main thing this neuron does is detect verbs that mean notifying or alerting someone (e.g. alert, inform, notify).

    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
    在住
    -1.98
    <td>
    -1.95
    '
    -1.82
    。】
    -1.70
    趿
    -1.70
    を使った
    -1.63
    邽
    -1.58
     a
    -1.57
     passend
    -1.56
     skrevet
    -1.55
    POSITIVE LOGITS
     you
    3.42
     us
    2.50
    useNewUrlParser
    2.02
     When
    2.00
    Whether
    1.98
    to
    1.95
    when
    1.94
    There
    1.91
    琑
    1.89
    b
    1.84
    Activations Density 0.045%

    No Known Activations