© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33038
    Prev
    Next
    INDEX
    Explanations

    .com / .org paths

    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
    :{
    -1.23
    kuun
    -1.20
    ANTAGES
    -1.18
     fotbal
    -1.16
     dall
    -1.15
    ﷲ
    -1.14
     kartą
    -1.12
    ֺ
    -1.12
    kram
    -1.11
    şit
    -1.10
    POSITIVE LOGITS
    particularly
    1.34
    especially
    1.27
    suddenly
    1.23
    昼食
    1.20
    ύ
    1.18
    Especially
    1.16
    场比赛
    1.16
     houver
    1.13
     seção
    1.11
     especialmente
    1.10
    Activations Density 0.226%

    No Known Activations