© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38556
    Prev
    Next
    INDEX
    Explanations

    your priority and satisfaction

    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
    Negative Logits
     for
    -2.14
     about
    -1.51
     světa
    -1.41
    itando
    -1.38
    hidup
    -1.35
     straips
    -1.34
    føring
    -1.33
    "",
    -1.33
    ांकि
    -1.30
    интере
    -1.27
    POSITIVE LOGITS
     it
    1.88
     you
    1.58
    蹩
    1.44
     your
    1.42
     pozosta
    1.34
    <strong>
    1.32
     its
    1.32
     ketiga
    1.32
     our
    1.30
     Reverso
    1.30
    Activations Density 0.055%

    No Known Activations