© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10549
    Prev
    Next
    INDEX
    Explanations

    only specific items

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

    This neuron strongly activates on the word “only,” marking phrases that emphasize exclusivity or limitation.

    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
     diğer
    -1.55
     otros
    -1.52
     outros
    -1.48
     to
    -1.41
    🗿
    -1.38
     autres
    -1.37
     meer
    -1.33
     még
    -1.32
    PSU
    -1.30
     complexe
    -1.30
    POSITIVE LOGITS
     those
    2.25
     who
    1.98
     where
    1.93
     when
    1.89
     znajdu
    1.73
     whose
    1.68
     what
    1.64
    ᠂
    1.56
     know
    1.55
     anerkannt
    1.53
    Activations Density 0.061%

    No Known Activations