© 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. 98920
    Prev
    Next
    INDEX
    Explanations

    distinguishing "other" items

    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
     \%$
    -1.55
    страции
    -1.48
     (!__
    -1.40
     notre
    -1.39
     таких
    -1.38
    鲽
    -1.37
    ouds
    -1.37
     зді
    -1.34
     پاکستان
    -1.34
    éges
    -1.33
    POSITIVE LOGITS
     the
    1.41
    ↵↵
    1.40
    B
    1.38
    n
    1.32
    R
    1.26
     pfle
    1.21
     with
    1.20
     finer
    1.18
    Â
    1.17
     verschiedener
    1.15
    Activations Density 0.069%

    No Known Activations