© 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. 34-GEMMASCOPE-RES-131K
    7. 56074
    Prev
    Next
    INDEX
    Explanations

    venues and locations

    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
     and
    -1.86
     zowel
    -1.21
     at
    -1.18
     vooral
    -1.06
     also
    -1.05
     Nachfrage
    -1.05
     incluyendo
    -1.02
    包括
    -1.01
     zarówno
    -0.99
     Erkrank
    -0.98
    POSITIVE LOGITS
     where
    1.34
    where
    1.16
     coû
    1.11
     following
    1.09
    راً
    1.07
     tristes
    1.07
     cesse
    1.05
    ſten
    1.03
     Polícia
    0.98
     feil
    0.98
    Activations Density 0.128%

    No Known Activations