© 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. 10-GEMMASCOPE-RES-131K
    4. 15087
    Prev
    Next
    INDEX
    Explanations

    markdown anchors and references

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

    The neuron fires on markdown/HTML-style in-page anchor references—i.e. “(#123)”-type tokens that point to numbered section or link IDs.

    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
     we
    -2.59
     That
    -2.59
     tetapi
    -2.55
     але
    -2.53
     But
    -2.41
    ↑↑↑</
    -2.41
     اما
    -2.23
     但
    -2.22
    that
    -2.20
    částí
    -2.20
    POSITIVE LOGITS
    ?’
    2.52
    
    2.41
    .
    2.38
     —
    2.36
    ’:
    2.34
    埽
    2.34
    ೣ
    2.31
    觉得
    2.31
     calendriers
    2.30
     poches
    2.27
    Activations Density 0.002%

    No Known Activations