© 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. 62802
    Prev
    Next
    INDEX
    Explanations

    alphabetically listed

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

    This neuron detects mentions of sorting or ordering items (e.g. references to “sort,” “order,” “arranged,” “alphabetically,” etc.).

    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
     känna
    -0.92
     prodigy
    -0.84
     lägga
    -0.83
     educativa
    -0.79
    <caption>
    -0.79
     LAY
    -0.79
     tvá
    -0.78
     changeable
    -0.77
     vlasy
    -0.76
    ágok
    -0.75
    POSITIVE LOGITS
     alphabetical
    4.28
     alphabetically
    4.06
     alpha
    3.53
    alpha
    3.36
     Alpha
    3.13
     alphabe
    2.97
    Alpha
    2.86
     alphabet
    2.64
     α
    2.52
     alfabe
    2.28
    Activations Density 0.066%

    No Known Activations