© 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. 113958
    Prev
    Next
    INDEX
    Explanations

    selecting an option

    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
     and
    -1.77
     their
    -1.30
     personnalité
    -1.29
    　　【
    -1.29
     anul
    -1.23
    　　《
    -1.22
    ámara
    -1.21
    كاتب
    -1.19
    áticos
    -1.16
     配信
    -1.16
    POSITIVE LOGITS
    ඍ
    1.48
    TintMode
    1.45
    ­
    1.44
     spp
    1.44
     weitgehend
    1.38
    珦
    1.38
    杁
    1.38
    𐬹
    1.34
     contender
    1.34
    问我
    1.34
    Activations Density 0.025%

    No Known Activations