© 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. 118296
    Prev
    Next
    INDEX
    Explanations

    substantial portions of the

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

    The neuron is simply lighting up on unusually rare or distinctive tokens (e.g. uncommon symbols, proper-names, code tags or legal-boilerplate keywords) – in other words, it flags high-information or low-frequency tokens.

    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
     hygienic
    -0.75
    resti
    -0.74
     نان
    -0.72
     silhouettes
    -0.72
    exc
    -0.71
    ordes
    -0.70
    ルフ
    -0.69
     レストラン
    -0.68
     Pistons
    -0.67
    ちん
    -0.67
    POSITIVE LOGITS
    Chung
    0.78
     Chung
    0.75
    履
    0.72
     梁
    0.68
    jel
    0.67
     Caro
    0.66
    siery
    0.66
     כך
    0.65
    地下
    0.63
     znám
    0.63
    Activations Density 0.056%

    No Known Activations