© 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. 48385
    Prev
    Next
    INDEX
    Explanations

    implement

    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
     {
    -1.34
     правительства
    -1.26
    んだけど
    -1.24
     najczęściej
    -1.22
     большого
    -1.22
     което
    -1.16
     nearing
    -1.15
     přip
    -1.15
    ('/:
    -1.14
    autres
    -1.13
    POSITIVE LOGITS
     with
    1.36
    ziona
    1.23
     such
    1.21
     tragé
    1.20
     a
    1.19
    tà
    1.16
     beker
    1.16
    糨
    1.16
     sò
    1.16
     automobili
    1.16
    Activations Density 0.102%

    No Known Activations