© 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. 9755
    Prev
    Next
    INDEX
    Explanations

    really or truly before words

    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
    Always
    -1.24
     always
    -1.23
    总体
    -1.19
    Siempre
    -1.16
     oczywiście
    -1.14
     sempre
    -1.13
     marginally
    -1.13
     vedno
    -1.10
    Our
    -1.09
     alltid
    -1.07
    POSITIVE LOGITS
     réellement
    1.30
     realmente
    1.23
    genu
    1.20
     truly
    1.19
     véritable
    1.19
     genuinely
    1.18
    真的
    1.18
     verdade
    1.17
     verdadera
    1.17
     verdadeira
    1.16
    Activations Density 0.032%

    No Known Activations