© 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. 101527
    Prev
    Next
    INDEX
    Explanations

    permission discussions

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

    The neuron activates on the word “permission” (or its plural form) wherever it appears.

    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
    '
    -2.28
    豢
    -2.02
    )
    -2.00
     appétit
    -2.00
    刂
    -1.99
     myriad
    -1.98
    ޚ
    -1.95
    冬天
    -1.92
     „
    -1.91
    蓴
    -1.88
    POSITIVE LOGITS
    焄
    2.52
     However
    2.30
    n
    2.27
     SOME
    2.17
     飯店
    2.09
    的态度
    2.09
    </sub>
    2.06
     The
    2.05
    趼
    1.99
     While
    1.98
    Activations Density 0.029%

    No Known Activations