© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    powers of 2 and bit shifts

    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
    </h1>
    -1.25
     two
    -1.23
     and
    -1.23
     anew
    -1.20
     if
    -1.15
    里有
    -1.15
     spurs
    -1.14
    ዐ
    -1.13
    because
    -1.12
     gul
    -1.11
    POSITIVE LOGITS
    菒
    1.60
    ઁ
    1.47
     Mbps
    1.39
    ꙰
    1.36
    gunakan
    1.35
    vantaged
    1.30
    ⎆
    1.29
    STRUCTION
    1.29
    kében
    1.26
    ⃨
    1.25
    Activations Density 0.077%

    No Known Activations