© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78370
    Prev
    Next
    INDEX
    Explanations

    names or entities followed by descriptions

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

    The neuron strongly activates on numeric tokens (years, addresses, IDs, counts) and related digit‐containing strings.

    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
    galaxy
    -0.75
    詡
    -0.74
    ท์
    -0.73
     nekaj
    -0.73
    ようですが
    -0.69
    弒
    -0.68
     Umfeld
    -0.68
    各个
    -0.68
    Understood
    -0.67
     levou
    -0.66
    POSITIVE LOGITS
    概率
    0.89
    DMETHOD
    0.84
    jando
    0.81
    ก
    0.79
    stoel
    0.79
     vetro
    0.78
     eti
    0.75
    ksamkeit
    0.74
     Mew
    0.74
     fertig
    0.74
    Activations Density 0.085%

    No Known Activations