© 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. 59775
    Prev
    Next
    INDEX
    Explanations

    copyright and author notices

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

    The neuron fires on individual hexadecimal characters or long runs of hex digits (e.g. in GUIDs, hashes, color codes, etc.).

    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
    itim
    -0.88
     diku
    -0.83
     habet
    -0.82
    iniai
    -0.79
    thest
    -0.77
    ̗
    -0.77
     trening
    -0.76
    olare
    -0.76
    ofluor
    -0.76
    явления
    -0.75
    POSITIVE LOGITS
    hips
    0.81
    really
    0.74
     respectively
    0.73
    fg
    0.73
     действительно
    0.73
     Hars
    0.71
     according
    0.69
    Really
    0.68
     кем
    0.68
    还是
    0.68
    Activations Density 0.179%

    No Known Activations