© 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. 39437
    Prev
    Next
    INDEX
    Explanations

    article introductions A, Q, Up, [

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

    The neuron fires on the opening of a Smarty‐style template conditional tag (e.g. “{if …}”).

    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
    ·
    -0.99
     -}
    -0.97
     bushing
    -0.92
    喎
    -0.91
    震惊
    -0.90
    ього
    -0.89
    く
    -0.88
    ارية
    -0.88
    нула
    -0.87
     fredag
    -0.87
    POSITIVE LOGITS
    beled
    0.93
     Even
    0.92
     Pokud
    0.91
    ündigung
    0.91
    嘹
    0.90
    гъл
    0.90
    cenary
    0.88
    Malware
    0.88
    ɳ
    0.87
    Incluso
    0.86
    Activations Density 0.000%

    No Known Activations