© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13773
    Prev
    Next
    INDEX
    Explanations

    letters, opinions, and direct address

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

    This neuron responds to section headings or article‐title markers—that is, tokens that appear at the start of a new news item or “Letter to the Editor” heading.

    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
    mability
    -1.34
    termilk
    -1.20
    terscotch
    -1.16
    ternut
    -1.15
    AnchorStyles
    -1.14
    datei
    -1.12
     viejas
    -1.08
    /}.
    -1.08
    音频
    -1.08
    famous
    -1.08
    POSITIVE LOGITS
     my
    1.56
     že
    1.16
     instead
    1.13
     I
    1.10
     regarding
    1.06
     Seems
    1.06
     meiner
    1.03
     rather
    1.03
     readers
    1.03
     cannot
    1.02
    Activations Density 0.040%

    No Known Activations