© 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. 22-GEMMASCOPE-RES-131K
    7. 38247
    Prev
    Next
    INDEX
    Explanations

    allowed to

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

    The neuron fires on expressions of permission or allowance—especially the word “allowed” (and its nearby prepositions).

    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
    甞
    -1.82
    螄
    -1.77
    ungalows
    -1.66
    ⎆
    -1.60
     continúas
    -1.60
    Erstellt
    -1.58
     rocas
    -1.57
     Allociné
    -1.56
    㐂
    -1.56
    tagHelper
    -1.55
    POSITIVE LOGITS
     to
    3.41
     in
    2.06
     禁止
    1.54
    .
    1.53
     participate
    1.44
    証拠
    1.43
    However
    1.40
    一種
    1.38
     Personally
    1.36
     Einen
    1.34
    Activations Density 0.011%

    No Known Activations