© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11932
    Prev
    Next
    INDEX
    Explanations

    yield, yield loss, yield improvement

    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
    hline
    -2.78
     seminal
    -2.45
    𝗲
    -2.39
     и
    -2.33
    uminense
    -2.20
    ᨕ
    -2.17
    嚷
    -2.16
    และ
    -2.16
    ﾄ
    -2.11
    észetes
    -2.09
    POSITIVE LOGITS
     Their
    2.81
    ଝ
    2.72
    ſelf
    2.30
    谞
    2.23
    部は
    2.23
    ︲
    2.20
    showed
    2.16
     of
    2.16
    崀
    2.16
    ꙰
    2.06
    Activations Density 0.010%

    No Known Activations