© 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. 22-GEMMASCOPE-RES-131K
    7. 12651
    Prev
    Next
    INDEX
    Explanations

    seemed

    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_22/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
     years
    -1.48
     months
    -1.34
    ":[{
    -1.09
     LoggerFactory
    -1.05
    Penulis
    -1.05
     then
    -1.04
    lecht
    -1.03
     vínculo
    -1.03
     médecin
    -1.03
    cción
    -1.02
    POSITIVE LOGITS
     constamment
    1.19
    cheinend
    1.10
     seemed
    1.09
     enough
    1.07
     fréquemment
    1.06
     经典
    1.05
     passim
    1.04
     quelquefois
    1.03
     ning
    1.02
    seemed
    1.02
    Activations Density 0.016%

    No Known Activations