© 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. 10-GEMMASCOPE-RES-131K
    7. 74856
    Prev
    Next
    INDEX
    Explanations

    chapter references

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

    The neuron activates strongly on explicit “chapter” headings (the word “chapter” often followed by a number).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    釹
    -2.47
    жении
    -2.45
     supports
    -2.31
     chega
    -2.30
     impedir
    -2.28
    眛
    -2.27
     môžu
    -2.25
    成田
    -2.23
     cumpli
    -2.22
     was
    -2.20
    POSITIVE LOGITS
    ある
    2.78
    an
    2.77
    re
    2.72
    In
    2.58
    ان
    2.56
    I
    2.50
    <td>
    2.48
    at
    2.45
    趼
    2.38
    man
    2.36
    Activations Density 0.007%

    No Known Activations