© 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. 70779
    Prev
    Next
    INDEX
    Explanations

    possessing qualities or states

    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
     then
    -1.28
     Then
    -1.10
     these
    -1.10
     بهتر
    -1.09
    ≦)
    -1.06
    𝐼
    -1.06
    nění
    -1.03
     тільки
    -1.02
     nyingi
    -1.02
     тогда
    -1.02
    POSITIVE LOGITS
     being
    1.22
     начала
    1.20
     is
    1.20
     subray
    1.16
    umably
    1.16
     sequence
    1.15
     nevy
    1.15
     Zuhause
    1.14
     vyk
    1.14
     alho
    1.13
    Activations Density 0.005%

    No Known Activations