© 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. 74007
    Prev
    Next
    INDEX
    Explanations

    code/technical terms

    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
     Some
    -1.34
     As
    -1.33
     get
    -1.29
     in
    -1.28
     create
    -1.26
     at
    -1.26
     Their
    -1.25
     While
    -1.24
     has
    -1.21
     To
    -1.20
    POSITIVE LOGITS
     plafon
    1.61
     tré
    1.55
     rése
    1.51
     konkrét
    1.41
     multicolore
    1.41
     rám
    1.40
     kabát
    1.38
     illustre
    1.38
     広場
    1.36
     éta
    1.34
    Activations Density 0.001%

    No Known Activations