© 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. 83895
    Prev
    Next
    INDEX
    Explanations

    designer names and brands

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    žiu
    -0.88
    épendance
    -0.88
    捗
    -0.87
    六年
    -0.80
     Torn
    -0.79
    éget
    -0.79
    セラー
    -0.79
    遵
    -0.79
    していきます
    -0.78
    茱
    -0.78
    POSITIVE LOGITS
     Collection
    0.93
    .__
    0.85
    verly
    0.84
     anahtar
    0.83
    素敵
    0.83
     münchen
    0.82
    .《
    0.82
    München
    0.81
     membuka
    0.80
    ☐
    0.80
    Activations Density 0.045%

    No Known Activations