© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16015
    Prev
    Next
    INDEX
    Explanations

    section titles or topics

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

    The neuron strongly activates on words that appear as part of section or subsection headings (i.e. document titles or header labels).

    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
    zeile
    -1.14
     撮り
    -1.13
     первым
    -1.13
     klien
    -1.12
     idee
    -1.12
     eduk
    -1.12
    BACA
    -1.11
     💕
    -1.11
     😄
    -1.10
     etui
    -1.09
    POSITIVE LOGITS
    :
    1.67
    </b>
    1.57
    </h2>
    1.54
     for
    1.46
     of
    1.44
    </strong>
    1.35
     and
    1.27
    !
    1.26
     with
    1.25
     Erkrank
    1.23
    Activations Density 0.050%

    No Known Activations