© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29033
    Prev
    Next
    INDEX
    Explanations

    street numbers and directions

    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
    いかがでしたか
    -1.81
     apparaissent
    -1.80
     cansado
    -1.69
     desmotiv
    -1.68
     самых
    -1.61
     maniere
    -1.54
    towa
    -1.53
     sólida
    -1.48
    arthed
    -1.48
     больших
    -1.48
    POSITIVE LOGITS
     of
    3.08
     for
    2.14
     not
    1.90
     at
    1.88
     from
    1.88
     with
    1.86
     where
    1.80
     on
    1.77
     in
    1.76
     who
    1.65
    Activations Density 0.025%

    No Known Activations