© 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. 64802
    Prev
    Next
    INDEX
    Explanations

    named entities and their descriptors

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

    The neuron strongly fires on individual tokens that are part of multi‐word named entities (proper names and titles).

    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
     and
    -1.37
     Ayrıca
    -1.36
     kompati
    -1.36
    któ
    -1.34
     bús
    -1.29
    ࿊
    -1.29
    fordshire
    -1.27
     unangemessene
    -1.27
     También
    -1.25
     folgte
    -1.24
    POSITIVE LOGITS
     Webseiten
    1.14
    g
    1.10
    そうですが
    1.09
     of
    1.07
     unwit
    1.02
     Serikat
    1.02
    ,
    0.97
    <i>
    0.97
     Adorable
    0.96
    G
    0.96
    Activations Density 0.132%

    No Known Activations