© 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. 54010
    Prev
    Next
    INDEX
    Explanations

    question starting with does

    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
    ㈠
    -0.79
     století
    -0.79
    </s>
    -0.78
    餃子
    -0.78
     mehrere
    -0.75
     języ
    -0.75
    diteur
    -0.75
    ！(
    -0.74
     Fórmula
    -0.73
     покупке
    -0.73
    POSITIVE LOGITS
     drinking
    1.11
     eating
    0.88
    飲んで
    0.81
     estando
    0.80
     Saw
    0.79
     FILTER
    0.78
     合金
    0.77
     unis
    0.76
     ati
    0.76
     Medicare
    0.75
    Activations Density 0.017%

    No Known Activations