© 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. 76900
    Prev
    Next
    INDEX
    Explanations

    strawberry contexts

    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
     telur
    -0.90
    branches
    -0.82
     BRANCH
    -0.81
     Branches
    -0.78
     RTX
    -0.78
     Meridian
    -0.78
    spiel
    -0.76
     branches
    -0.76
     Bade
    -0.75
     Mop
    -0.75
    POSITIVE LOGITS
    🍓
    1.89
     strawberry
    1.75
     Strawberry
    1.55
     strawberries
    1.54
    Strawberry
    1.50
    strawberry
    1.38
    Straw
    1.31
     Strawberries
    1.23
     草莓
    1.13
    straw
    1.09
    Activations Density 0.015%

    No Known Activations