© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92696
    Prev
    Next
    INDEX
    Explanations

    food platters and samplers

    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
    ranie
    -0.93
    óngase
    -0.81
    uoš
    -0.73
    浬
    -0.71
    Pró
    -0.71
     redi
    -0.70
    Jó
    -0.70
     було
    -0.69
    annelse
    -0.69
    Conven
    -0.68
    POSITIVE LOGITS
     platter
    2.28
     sampler
    1.65
     tray
    1.47
     Sampler
    1.43
     assortment
    1.43
     assorted
    1.37
     sharing
    1.32
    拼
    1.30
    sampler
    1.24
    Sharing
    1.18
    Activations Density 0.013%

    No Known Activations