© 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. 22-GEMMASCOPE-RES-131K
    7. 65960
    Prev
    Next
    INDEX
    Explanations

    people or roles followed by descriptions

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

    The neuron flags words denoting people’s roles or titles (e.g. quarterback, coach, candidate, president, comedian, player).

    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
    میزی
    -1.10
    难怪
    -1.07
    TIPOS
    -1.05
    PÁG
    -1.05
    OBJETIVO
    -1.02
     treści
    -1.02
     horrid
    -0.99
    CARACTERIST
    -0.99
    人たち
    -0.98
    全都
    -0.98
    POSITIVE LOGITS
     bernama
    1.36
     who
    1.33
    [!
    1.18
     namely
    1.16
    lamiento
    1.14
    eados
    1.13
     such
    1.11
    .*;
    1.08
     namens
    1.07
    »;
    1.05
    Activations Density 0.033%

    No Known Activations