© 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. 34-GEMMASCOPE-RES-131K
    4. 4143
    Prev
    Next
    INDEX
    Explanations

    Code, emails, and programming languages

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

    The neuron is keyed to non‐natural‐language symbols and tokens—things like code or markup punctuation, operators, and other special‐character sequences.

    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
     Thirteen
    -0.98
    為
    -0.90
     thirteenth
    -0.84
    Thirteen
    -0.77
     Thirteenth
    -0.77
    为
    -0.77
     Mantra
    -0.76
    getOr
    -0.74
    ҙ
    -0.74
     thirteen
    -0.73
    POSITIVE LOGITS
     Schnitt
    0.69
     At
    0.69
     Сейчас
    0.68
    rahman
    0.66
    its
    0.66
     uzys
    0.65
    ResultSet
    0.65
    ặt
    0.64
     tabulated
    0.64
    સ
    0.63
    Activations Density 0.459%

    No Known Activations