© 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. 22-GEMMASCOPE-RES-131K
    4. 68822
    Prev
    Next
    INDEX
    Explanations

    quoted strings

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

    The neuron fires on numeric literals (sequences of digits) in the code.

    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
     that
    -1.84
     hunde
    -1.69
    angkap
    -1.66
     向け
    -1.66
    providedIn
    -1.59
     pistolet
    -1.55
    Prí
    -1.55
    Zubereitung
    -1.52
    Čo
    -1.51
    Those
    -1.50
    POSITIVE LOGITS
     “
    2.09
    '
    1.94
     ‘
    1.84
    *
    1.79
    -
    1.76
    ’
    1.73
    k
    1.61
     '
    1.59
    h
    1.55
    b
    1.54
    Activations Density 0.011%

    No Known Activations