© 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. 40086
    Prev
    Next
    INDEX
    Explanations

    repeated PWN

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

    The neuron fires on tokens that are numeric—i.e. sequences of digits representing numbers.

    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
    насе
    -0.89
     sandalias
    -0.88
    ческого
    -0.85
    corrhi
    -0.84
     年代
    -0.83
     ће
    -0.83
    emiah
    -0.82
     encontre
    -0.81
    nowa
    -0.81
     levels
    -0.81
    POSITIVE LOGITS
    wing
    0.85
    eline
    0.78
    ić
    0.78
    Bash
    0.77
     vill
    0.76
    Wing
    0.75
     соответству
    0.73
     Hotspot
    0.73
    nin
    0.73
    íř
    0.73
    Activations Density 0.010%

    No Known Activations