© 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. 104345
    Prev
    Next
    INDEX
    Explanations

    phrases ending with period

    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
     pelatih
    -1.05
    Törté
    -1.02
     estimés
    -1.00
    Ƕ
    -0.98
     antwoord
    -0.98
     stratég
    -0.97
    aure
    -0.93
     ľah
    -0.92
    Morfologia
    -0.91
    ס
    -0.91
    POSITIVE LOGITS
     continuare
    1.07
     vini
    0.97
     bici
    0.96
     pulsa
    0.94
     luce
    0.93
     competen
    0.93
     perifer
    0.92
     monaster
    0.92
     noti
    0.89
     impon
    0.89
    Activations Density 0.010%

    No Known Activations