© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75373
    Prev
    Next
    INDEX
    Explanations

    subject of

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

    The neuron activates on tokens in “X is/are a part of Y” or “one of my favorite Y”–style constructions that signal something belonging to or included in a larger whole.

    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
    quot
    -1.10
    pecies
    -1.09
    satunya
    -1.07
    omeness
    -1.07
    』
    -1.06
    ்
    -1.05
    %">
    -1.03
     клини
    -1.03
    ndash
    -1.02
     sitesinde
    -1.02
    POSITIVE LOGITS
     our
    1.59
     unserer
    1.41
     of
    1.25
     nuestro
    1.17
     my
    1.08
     nuestra
    1.08
     currently
    1.05
     another
    1.02
     in
    1.02
     America
    1.01
    Activations Density 0.053%

    No Known Activations