© 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. 22-GEMMASCOPE-RES-131K
    7. 38441
    Prev
    Next
    INDEX
    Explanations

    questions starting with 'is' or 'i'

    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_22/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
    sikker
    -1.04
    álbum
    -1.01
     his
    -0.97
    Wszyst
    -0.96
    Licz
    -0.94
    usual
    -0.93
     světě
    -0.91
    Bardzo
    -0.89
    bagno
    -0.88
    𝗪
    -0.88
    POSITIVE LOGITS
     only
    1.01
     simply
    0.91
     только
    0.90
    mond
    0.88
     just
    0.88
     reikia
    0.88
     there
    0.85
     ésta
    0.85
    await
    0.84
     торгов
    0.84
    Activations Density 0.128%

    No Known Activations