© 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. 73697
    Prev
    Next
    INDEX
    Explanations

    Linden St, Bally, anise seed, Zee TV

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

    The neuron lights up on specific named‐entity tokens—proper names of people, places, brands, 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
    the
    -2.97
    o
    -2.92
    咴
    -2.47
    蟜
    -2.44
    wiście
    -2.39
    e
    -2.31
    a
    -2.31
    VERY
    -2.30
    IN
    -2.22
     riuscito
    -2.22
    POSITIVE LOGITS
    न
    2.44
    あります
    2.23
     There
    2.22
     sorprendente
    2.22
    ють
    2.20
    .”
    2.19
     sorprend
    2.16
    五个
    2.16
     Pingback
    2.14
    ский
    2.13
    Activations Density 0.022%

    No Known Activations