© 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. 12896
    Prev
    Next
    INDEX
    Explanations

    limiting availability and access

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

    The neuron activates on instances of “limit” (and its morphological variants like “limiting,” “limits,” etc.) indicating constraints or restrictions.

    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
    CHREIBUNG
    -1.01
    📬
    -0.98
     tudom
    -0.95
    -------
    -0.93
    nne
    -0.92
     behandelt
    -0.91
     dizaines
    -0.91
    ircraft
    -0.91
    艰难
    -0.90
    zné
    -0.89
    POSITIVE LOGITS
     amount
    1.35
     scope
    1.30
     access
    1.21
     how
    1.20
     extent
    1.17
     permissible
    1.13
     activities
    1.09
     number
    1.09
     ability
    1.07
    öglichkeiten
    1.05
    Activations Density 0.061%

    No Known Activations