© 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. 10-GEMMASCOPE-RES-131K
    7. 14419
    Prev
    Next
    INDEX
    Explanations

    access and use restrictions

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

    The neuron activates on words and phrases related to “restriction” or its absence—e.g. unrestricted, restriction, uninhibited, etc.

    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
    嘥
    -2.23
    삵
    -2.22
    沵
    -2.16
    糴
    -2.13
     adesivo
    -2.08
     可愛い
    -2.06
     墊
    -2.02
    䛗
    -1.99
     accessoires
    -1.95
     changer
    -1.91
    POSITIVE LOGITS
     Many
    2.33
     say
    2.19
     )
    2.16
     From
    2.11
     -
    2.09
     w
    2.06
     from
    2.05
     ;
    2.00
     Because
    1.99
     While
    1.98
    Activations Density 0.007%

    No Known Activations