© 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. 10-GEMMASCOPE-RES-131K
    7. 67266
    Prev
    Next
    INDEX
    Explanations

    words starting with sna

    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_10/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
    ’
    -3.25
    ↵
    -3.13
    榈
    -2.67
    ”),
    -2.53
    </sup>
    -2.52
     et
    -2.44
     biasanya
    -2.39
    If
    -2.34
     mesmas
    -2.33
    呖
    -2.33
    POSITIVE LOGITS
    anyeol
    2.70
     snag
    2.67
     circumvent
    2.45
     ponemos
    2.36
    ntesis
    2.36
    sipasi
    2.34
    鼋
    2.31
    愿望
    2.28
    étation
    2.27
     welchem
    2.23
    Activations Density 0.005%

    No Known Activations