© 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. 34-GEMMASCOPE-RES-131K
    7. 80882
    Prev
    Next
    INDEX
    Explanations

    granting permission

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

    The neuron fires on occurrences of “permit”/“permission” (and related forms like “permitted”) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    i
    -1.06
     \
    -0.95
     ngoài
    -0.95
    deepEqual
    -0.93
     לכם
    -0.92
     endangered
    -0.88
    ch
    -0.87
    is
    -0.86
     zä
    -0.85
    ｶ
    -0.84
    POSITIVE LOGITS
    tivity
    1.30
    ómo
    1.00
    tees
    0.97
     holder
    0.93
    tance
    0.93
    tensorflow
    0.91
    uese
    0.91
    ouns
    0.91
    OECD
    0.90
     canter
    0.90
    Activations Density 0.016%

    No Known Activations