© 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. 22-GEMMASCOPE-RES-131K
    7. 26092
    Prev
    Next
    INDEX
    Explanations

    list items, references, descriptions

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

    The neuron detects numeric tokens in bibliographic citation contexts (e.g. volume or issue numbers in references).

    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
     strongly
    -1.00
     changed
    -0.94
     ministros
    -0.93
     created
    -0.91
     strategy
    -0.88
     within
    -0.88
     automático
    -0.87
     seier
    -0.86
     in
    -0.86
     modified
    -0.86
    POSITIVE LOGITS
    ENIX
    1.12
     Atención
    1.03
     flamboyant
    1.02
     tranquil
    1.00
     ornate
    0.99
     majestic
    0.96
     gigantic
    0.96
     frecuentemente
    0.96
     opulent
    0.95
    从来
    0.93
    Activations Density 0.000%

    No Known Activations