© 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. 116702
    Prev
    Next
    INDEX
    Explanations

    int nx, obl cad, Ole Ctl

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

    The neuron fires on statistical terminology—especially references to Gaussian distributions and summary‐statistic functions (e.g. “Gaussian,” “mean,” “std”).

    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
    ®:
    -0.83
     Giovanna
    -0.81
     initiating
    -0.78
    ).....
    -0.77
     weekly
    -0.77
     setti
    -0.76
    世代
    -0.75
     berguna
    -0.74
     редко
    -0.74
    vna
    -0.74
    POSITIVE LOGITS
    outlined
    0.90
     vzd
    0.88
    Trav
    0.87
     referrerpolicy
    0.84
     театр
    0.82
    curr
    0.82
    秶
    0.82
    ݯ
    0.81
    phous
    0.80
     intptr
    0.80
    Activations Density 0.143%

    No Known Activations