© 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. 84014
    Prev
    Next
    INDEX
    Explanations

    http:// URLs and schemas

    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
    monės
    -1.13
    :^{
    -1.03
    kram
    -1.02
    köp
    -1.02
    lägen
    -1.02
     have
    -1.00
     failed
    -0.98
    cautionary
    -0.98
    läge
    -0.98
    arif
    -0.98
    POSITIVE LOGITS
    这般
    1.23
    וּ
    1.15
    蝼
    1.07
    抬起头
    1.05
     причем
    1.03
     dessutom
    1.03
    förmig
    1.02
    erdere
    1.02
    частли
    1.02
    itete
    1.01
    Activations Density 0.080%

    No Known Activations