© 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. 75670
    Prev
    Next
    INDEX
    Explanations

    code initialization or methods

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

    The neuron fires on the “dot” token in code—i.e. the member-access/method-call separator (object.property or object.method()) in programming language snippets.

    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
     év
    -0.85
     inflatable
    -0.85
     betaling
    -0.80
    glLoad
    -0.79
     charlotte
    -0.78
     penyakit
    -0.76
     evangel
    -0.75
     Solidar
    -0.75
     wrze
    -0.74
     wales
    -0.74
    POSITIVE LOGITS
     naszych
    1.24
     naszego
    1.11
     our
    1.09
     нашим
    1.08
     nasze
    0.98
     naszej
    0.96
     mūsų
    0.94
     sicuro
    0.92
     from
    0.89
     вашим
    0.88
    Activations Density 0.119%

    No Known Activations