© 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. 25468
    Prev
    Next
    INDEX
    Explanations

    introduction to Nine-patch graphics

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

    The neuron is picking up on YAML/Markdown front‐matter metadata (keys and their quoted values) at the top of a document.

    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
     katholischen
    -1.19
     Reised
    -1.16
    先日
    -1.16
    やはり
    -1.09
    やっぱり
    -1.09
     ministres
    -1.09
    rían
    -1.08
    ığım
    -1.08
     Hva
    -1.07
     ваз
    -1.03
    POSITIVE LOGITS
     you
    2.50
     your
    1.69
     to
    1.45
     if
    1.30
     eſ
    1.25
     filós
    1.24
    这本书
    1.23
     You
    1.22
     ſer
    1.21
     стене
    1.16
    Activations Density 0.065%

    No Known Activations