© 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. 59982
    Prev
    Next
    INDEX
    Explanations

    titles before names

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

    The neuron selectively responds to numeric tokens (e.g., years, page or section numbers, vote counts).

    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
    そば
    -0.87
     Obama
    -0.81
    джан
    -0.73
     Uhuru
    -0.73
    ,}
    -0.73
    Obama
    -0.72
    !!"
    -0.72
    ")
    -0.70
     zult
    -0.70
    ',)
    -0.70
    POSITIVE LOGITS
    Instantiation
    0.85
     שמע
    0.82
     Sevilla
    0.79
    리스
    0.73
    URER
    0.71
    Digital
    0.71
     прекрасно
    0.71
     мысли
    0.70
    чества
    0.70
     ২০
    0.69
    Activations Density 0.060%

    No Known Activations