© 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. 22-GEMMASCOPE-RES-131K
    7. 65046
    Prev
    Next
    INDEX
    Explanations

    interjections and abbreviations

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

    The neuron spots numeric tokens (especially citation or reference digits) 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_22/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
    ୈ
    -1.13
     był
    -1.09
    Rptr
    -1.08
    BackColor
    -1.06
    <th>
    -1.04
     aikana
    -1.03
    ጴ
    -1.03
    StructEnd
    -1.03
     szczególnie
    -1.03
    пись
    -1.02
    POSITIVE LOGITS
    阉
    1.08
     離
    1.02
     ploy
    0.98
    一開始
    0.94
    軟體
    0.91
    MODERN
    0.91
     Inde
    0.90
    その他の
    0.90
     階
    0.88
    ということを
    0.87
    Activations Density 0.000%

    No Known Activations