© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92839
    Prev
    Next
    INDEX
    Explanations

    council meeting discussion

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

    The neuron fires on the punctuation and formatting that mark the break between a dateline (e.g. “EAST PAL-ESTINE –”) or headline and the body of a news article—that is, on the section‐delimiter dashes, headings, and end‐of‐lead periods.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     augusti
    -0.93
    ✆
    -0.91
    Authors
    -0.90
     KEYS
    -0.90
    Employees
    -0.85
    authorities
    -0.85
    IMAS
    -0.85
     kaynağından
    -0.85
    Says
    -0.83
     Dik
    -0.83
    POSITIVE LOGITS
     board
    2.06
     council
    1.86
     committee
    1.77
     Chairman
    1.60
     Board
    1.53
     several
    1.48
     chairman
    1.46
     Council
    1.41
     members
    1.38
     councillors
    1.36
    Activations Density 0.016%

    No Known Activations