© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111238
    Prev
    Next
    INDEX
    Explanations

    role of

    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_10/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
    "'
    -1.54
    祧
    -1.48
    Viitteet
    -1.43
     verwendet
    -1.38
     noticed
    -1.37
     bureaux
    -1.37
     большая
    -1.35
    ܊
    -1.32
     старый
    -1.30
     Either
    -1.30
    POSITIVE LOGITS
     your
    1.78
    Дина
    1.58
     emphat
    1.41
    徕
    1.34
    了你
    1.33
     napisa
    1.32
     Role
    1.32
    ulturen
    1.31
     транспор
    1.31
    providedIn
    1.30
    Activations Density 0.047%

    No Known Activations