© 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. 11525
    Prev
    Next
    INDEX
    Explanations

    cylindrical objects and shapes

    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
    ſſer
    -2.52
    ا
    -2.50
    r
    -2.50
     segar
    -2.39
     kompeti
    -2.36
     []
    -2.34
     varm
    -2.31
     cuci
    -2.30
     ""))
    -2.30
    aaaa
    -2.27
    POSITIVE LOGITS
     sporadic
    2.69
     erforder
    2.63
     perfected
    2.39
     con
    2.27
     oreja
    2.19
    ですので
    2.19
     свою
    2.17
     registrado
    2.17
    <tr>
    2.16
     verstanden
    2.16
    Activations Density 0.012%

    No Known Activations