© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13121
    Prev
    Next
    INDEX
    Explanations

    describing a specific type or part

    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
     these
    -1.79
     I
    -1.62
     my
    -1.57
     These
    -1.23
     Regionen
    -1.15
    太多的
    -1.14
    These
    -1.14
     laku
    -1.12
     konsep
    -1.10
    ིན་
    -1.09
    POSITIVE LOGITS
     apenas
    1.48
     continuación
    1.36
    Viitteet
    1.27
     sánh
    1.23
    Հ
    1.22
     aurez
    1.20
     näher
    1.19
     adalah
    1.18
    ῾
    1.17
     location
    1.16
    Activations Density 0.001%

    No Known Activations