© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110586
    Prev
    Next
    INDEX
    Explanations

    protective action

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

    The neuron fires on numeric tokens (digits or numbers) 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
     by
    -1.66
     of
    -1.54
     or
    -1.48
    ,"
    -1.45
     its
    -1.45
    ."
    -1.45
     that
    -1.41
     "
    -1.39
    );
    -1.38
     podría
    -1.38
    POSITIVE LOGITS
    ſelves
    1.63
     assise
    1.41
    jedno
    1.41
    Eglise
    1.38
    podob
    1.37
    UCIÓN
    1.35
     dreapta
    1.34
     barbati
    1.33
     victime
    1.31
     viata
    1.31
    Activations Density 0.000%

    No Known Activations