© 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. 34-GEMMASCOPE-RES-131K
    7. 3388
    Prev
    Next
    INDEX
    Explanations

    citations and authors

    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_34/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
     sesi
    -1.29
     galeri
    -1.27
     tica
    -1.23
     durer
    -1.19
     galeria
    -1.17
     endi
    -1.13
     tatu
    -1.13
     soldat
    -1.07
     administratif
    -1.07
     romantis
    -1.06
    POSITIVE LOGITS
    وضح
    1.31
    下さ
    1.08
     gostar
    1.07
    ),
    1.07
     terceiros
    1.06
     Многие
    1.05
    },
    1.03
     possíveis
    1.01
    ثل
    1.01
     including
    1.01
    Activations Density 0.054%

    No Known Activations