© 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. 48511
    Prev
    Next
    INDEX
    Explanations

    diet plans and health programs

    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
    äte
    -0.94
     Storia
    -0.93
    キャベツ
    -0.80
    醤油
    -0.80
    プラグ
    -0.79
    ਲ
    -0.79
    indung
    -0.76
     fintech
    -0.76
     diverted
    -0.76
    ில
    -0.76
    POSITIVE LOGITS
     Mediterranean
    1.55
     diet
    1.44
     plan
    1.34
    Mediterranean
    1.28
     DASH
    1.22
     program
    1.09
     cleanse
    1.09
     reset
    1.02
     Reset
    1.02
     approach
    0.98
    Activations Density 0.036%

    No Known Activations