© 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. 58365
    Prev
    Next
    INDEX
    Explanations

    foreign characters and specific names

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

    The neuron flags garbled or non-standard characters (e.g. stray Unicode/HTML entities like “â,” “€” etc.) in the text.

    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
    ต่างๆ
    -0.88
     intricacies
    -0.82
     proved
    -0.82
     naselje
    -0.81
    òng
    -0.79
     may
    -0.78
     from
    -0.77
     other
    -0.77
     示例
    -0.77
     Quite
    -0.75
    POSITIVE LOGITS
    Ǫ
    0.94
    📽
    0.90
     FUCKING
    0.90
     berech
    0.85
     magnificent
    0.85
    fucking
    0.84
     fabulous
    0.84
     fantastic
    0.82
    でに
    0.81
     ƙ
    0.81
    Activations Density 0.002%

    No Known Activations