© 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. 39803
    Prev
    Next
    INDEX
    Explanations

    project configuration and paths

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

    The neuron fires on numeric tokens, especially long sequences of digits.

    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
     curiously
    -0.82
     may
    -0.78
     strongly
    -0.77
    UserService
    -0.76
    HANDLING
    -0.71
     стол
    -0.70
     заранее
    -0.70
    mau
    -0.69
    ducers
    -0.69
    RANDOM
    -0.69
    POSITIVE LOGITS
    忪
    0.98
     maș
    0.86
     fentanyl
    0.85
    wanzig
    0.84
    EndInit
    0.84
     апреля
    0.83
    øren
    0.83
     μας
    0.82
    עי
    0.82
     nike
    0.82
    Activations Density 0.043%

    No Known Activations