© 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. 34-GEMMASCOPE-RES-131K
    7. 48832
    Prev
    Next
    INDEX
    Explanations

    toy or toys

    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
     graphql
    -0.76
     NAK
    -0.75
    совершен
    -0.75
    ไตล์
    -0.72
    atsch
    -0.71
    ările
    -0.71
    GraphicsUnit
    -0.71
    メートル
    -0.70
    ช่อง
    -0.69
    હ
    -0.69
    POSITIVE LOGITS
     toys
    4.91
     toy
    4.41
     Toys
    3.44
    toys
    3.22
    toy
    3.11
    Toy
    3.06
    Toys
    2.95
     Toy
    2.89
    玩具
    2.77
     juguetes
    2.58
    Activations Density 0.076%

    No Known Activations