© 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. 57491
    Prev
    Next
    INDEX
    Explanations

    well drained soil, Lemon Drops

    np_acts-logits-general · gemini-2.5-flash-lite

    food and cooking-related ingredients and terms in instructional content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     abrió
    -0.71
    autant
    -0.71
    índ
    -0.69
    WithIdentifier
    -0.69
    عر
    -0.68
     lads
    -0.67
     inimigo
    -0.66
    Supplemental
    -0.66
    Whilst
    -0.65
     ifade
    -0.65
    POSITIVE LOGITS
     Rochester
    0.77
    regexp
    0.77
     Aujourd
    0.75
     Piazza
    0.74
     Manson
    0.73
     readers
    0.73
     concealed
    0.72
    ه‌ی
    0.71
    יקה
    0.71
     ľudí
    0.71
    Activations Density 0.010%

    No Known Activations