© 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. 10-GEMMASCOPE-RES-131K
    7. 68815
    Prev
    Next
    INDEX
    Explanations

    place of origin

    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
     others
    -1.52
    <bos>
    -1.38
     things
    -1.28
    AppRoutingModule
    -1.18
    iteit
    -1.16
     some
    -1.15
     not
    -1.14
     articles
    -1.13
     claves
    -1.13
     \&
    -1.13
    POSITIVE LOGITS
     grijs
    1.61
     voelt
    1.45
     leichte
    1.44
     who
    1.43
    极了
    1.38
    .}(
    1.32
    flexible
    1.27
     kaca
    1.27
     жк
    1.26
     perak
    1.26
    Activations Density 0.059%

    No Known Activations