© 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. 34610
    Prev
    Next
    INDEX
    Explanations

    location and settings

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

    The neuron fires on common plural nouns (words ending in an “-s” that denote items or categories, e.g. “intervals,” “devices,” “settings,” “regions”).

    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
     cinturón
    -0.99
     aliento
    -0.97
     Niemand
    -0.96
     größe
    -0.94
    malte
    -0.91
    buddha
    -0.91
    isering
    -0.91
    fand
    -0.90
    ypeł
    -0.90
    hhhhhhhh
    -0.90
    POSITIVE LOGITS
    での
    1.64
    における
    1.08
    bp
    1.02
    瞅
    1.00
    で
    0.97
    上的
    0.94
    天候
    0.93
    雫
    0.91
    以外
    0.90
    調味料
    0.90
    Activations Density 0.203%

    No Known Activations