© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115995
    Prev
    Next
    INDEX
    Explanations

    opening punctuation or conjunctions

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

    The neuron strongly lights up on numeric tokens (digits and numbers) and related formatting.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Selecting
    -0.83
     hâ
    -0.81
    volen
    -0.81
    unggah
    -0.81
     võ
    -0.79
     heren
    -0.79
     jao
    -0.78
    buzz
    -0.77
    hancing
    -0.75
     suure
    -0.75
    POSITIVE LOGITS
     expla
    0.84
    Chalk
    0.80
    Mi
    0.77
     fill
    0.75
    voix
    0.74
     Spectrum
    0.73
    readlines
    0.73
     Explained
    0.73
     człon
    0.72
    켜
    0.71
    Activations Density 0.031%

    No Known Activations