© 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. 22-GEMMASCOPE-RES-131K
    7. 25861
    Prev
    Next
    INDEX
    Explanations

    titles and technical terms

    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
    Θ
    -1.05
     poliuret
    -1.00
    度
    -0.96
    Λ
    -0.96
    Ξ
    -0.91
     Addresses
    -0.91
     Betrag
    -0.90
     géant
    -0.90
    　　[
    -0.90
    Ρ
    -0.88
    POSITIVE LOGITS
     supported
    1.08
     business
    0.93
    достатки
    0.89
    様な
    0.88
     your
    0.88
     škoda
    0.87
     During
    0.87
     service
    0.85
     лук
    0.85
     একটি
    0.84
    Activations Density 0.047%

    No Known Activations