© 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. 14205
    Prev
    Next
    INDEX
    Explanations

    not found

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

    This neuron activates on negation words—especially “not”—in error‐message contexts (e.g. “not found,” “not updated,” “not set”).

    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
     a
    -2.47
     kteří
    -1.78
     of
    -1.47
     "..\..\
    -1.46
    '));
    -1.44
    腹部
    -1.43
    ÍTULO
    -1.40
    ),
    -1.40
    "},
    -1.40
    真的
    -1.37
    POSITIVE LOGITS
    這種
    1.56
    經常
    1.54
    當時
    1.50
    還會
    1.49
    還能
    1.48
    給你
    1.45
    这么多
    1.42
    讓我
    1.41
    lequin
    1.41
    儼
    1.41
    Activations Density 0.034%

    No Known Activations