© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42909
    Prev
    Next
    INDEX
    Explanations

    customers, audience, residents, users, fans, players, Americans, clients

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

    This neuron detects nouns referring to groups of people or target audiences (e.g., customers, audience, users, gamers, residents, fans).

    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
    entamiento
    -1.32
    giatan
    -1.24
    ⩴
    -1.23
     the
    -1.22
     ſont
    -1.20
     miljoen
    -1.19
    ctuaries
    -1.18
    ینده
    -1.16
    Tribune
    -1.16
     Brasileiro
    -1.16
    POSITIVE LOGITS
     those
    1.48
     
    1.33
     такі
    1.33
     there
    1.31
     mají
    1.31
     when
    1.30
    を見ると
    1.28
     it
    1.28
     experimentado
    1.27
    dyž
    1.26
    Activations Density 0.060%

    No Known Activations