© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32615
    Prev
    Next
    INDEX
    Explanations

    define sd quantify

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

    The neuron fires strongly on individual hexadecimal characters or byte‐pair tokens within long hash‐ or address‐like hexadecimal 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
     ounce
    -0.77
    Bö
    -0.77
     thậm
    -0.77
    的同时
    -0.76
    backing
    -0.75
    powied
    -0.73
     вспом
    -0.73
    낀
    -0.72
     Ligne
    -0.71
     kool
    -0.71
    POSITIVE LOGITS
    نص
    0.82
    ógicos
    0.76
    Away
    0.74
    ׃
    0.73
     away
    0.73
     Away
    0.72
     Martin
    0.71
    ➐
    0.70
     Ath
    0.69
     everyone
    0.68
    Activations Density 0.068%

    No Known Activations