© 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. 80044
    Prev
    Next
    INDEX
    Explanations

    institutions and places

    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
    ţilor
    -1.20
     solde
    -1.15
     ogrom
    -1.15
     algodón
    -1.11
    Vlastnosti
    -1.10
     faldas
    -1.07
    Zdroje
    -1.06
     merveille
    -1.06
    食べられる
    -1.05
    ⿷
    -1.05
    POSITIVE LOGITS
     in
    1.41
     is
    1.35
    ...
    1.32
     can
    1.19
    ....
    1.13
     곳
    1.11
    ...(
    1.07
     best
    1.05
     剑
    1.01
     management
    0.99
    Activations Density 0.059%

    No Known Activations