© 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. 10-GEMMASCOPE-RES-131K
    7. 86580
    Prev
    Next
    INDEX
    Explanations

    awake or opaque

    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
    ’
    -3.09
     he
    -2.91
     \
    -2.52
    </b>
    -2.50
    𖥧
    -2.47
     から
    -2.45
     ‘
    -2.39
    になるので
    -2.38
     необходимо
    -2.34
    わけ
    -2.31
    POSITIVE LOGITS
    ኞ
    2.36
    ственная
    2.30
    鷓
    2.28
    鋮
    2.20
    画像は
    2.19
    亅
    2.19
     светло
    2.17
    擻
    2.16
     plupart
    2.16
    年初
    2.13
    Activations Density 0.001%

    No Known Activations