© 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. 8208
    Prev
    Next
    INDEX
    Explanations

    to the

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

    the neuron consistently activates on numeric expressions (numbers and measurements) in the text.

    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
    _
    -1.89
    these
    -1.63
    рин
    -1.58
     lieto
    -1.55
    while
    -1.53
    //
    -1.50
     électriques
    -1.49
     två
    -1.49
    which
    -1.45
     هذه
    -1.45
    POSITIVE LOGITS
     by
    1.87
     Süden
    1.80
     to
    1.76
     That
    1.69
     where
    1.63
    Ingrédients
    1.59
     out
    1.53
    ("")]
    1.50
     "..\..\..\
    1.45
    鄔
    1.44
    Activations Density 0.067%

    No Known Activations