© 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. 69298
    Prev
    Next
    INDEX
    Explanations

    into or direction

    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
    Extinguishing
    -1.30
     llevado
    -1.24
    ’).
    -1.23
     ermöglichen
    -1.21
     lampu
    -1.20
     Each
    -1.20
    ']=='
    -1.18
     ocasi
    -1.18
     would
    -1.16
    ’)
    -1.16
    POSITIVE LOGITS
     [
    1.22
    </strong>
    1.15
    大众
    1.09
    itisation
    1.07
    几种
    1.07
    во
    1.03
    ık
    0.99
    Iacute
    0.98
    rogens
    0.96
    ı
    0.96
    Activations Density 0.046%

    No Known Activations