© 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. 57398
    Prev
    Next
    INDEX
    Explanations

    names and subsequent words

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

    The neuron is detecting named entities and other key proper‐noun or technical‐term tokens (e.g. people’s names, places, organizations, specialized process names).

    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
     compared
    -1.33
     together
    -1.13
     vías
    -1.05
     attraverso
    -0.98
     больше
    -0.97
     juntamente
    -0.96
    嚎
    -0.93
     práctico
    -0.93
     contrasted
    -0.93
     wraz
    -0.92
    POSITIVE LOGITS
     in
    2.56
     on
    1.61
    ในการ
    1.45
     as
    1.40
     dalam
    1.38
     who
    1.16
    ใน
    1.04
     در
    1.02
     quien
    1.02
     avantage
    1.02
    Activations Density 0.075%

    No Known Activations