© 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. 10-GEMMASCOPE-RES-131K
    7. 73300
    Prev
    Next
    INDEX
    Explanations

    Chapman and PostgreSQL names

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

    The neuron is a named‐entity detector, firing strongly on proper nouns (people’s names, place names, software names, etc.).

    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
     iſt
    -3.00
    咵
    -2.50
    椟
    -2.48
    {
    -2.47
    ￪
    -2.39
    ского
    -2.38
    眥
    -2.34
    蕖
    -2.33
     unſ
    -2.31
    IANGLES
    -2.25
    POSITIVE LOGITS
    D
    3.23
    P
    2.48
    section
    2.38
    S
    2.33
    U
    2.30
    B
    2.27
    R
    2.25
    i
    2.25
    逦
    2.23
    на
    2.22
    Activations Density 0.005%

    No Known Activations