© 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. 28160
    Prev
    Next
    INDEX
    Explanations

    my favorite noun

    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
     your
    -1.11
    了不少
    -0.98
     Spisak
    -0.92
     pouze
    -0.91
     nécessaire
    -0.90
     peinados
    -0.90
     benötigen
    -0.89
     |
    -0.89
     District
    -0.88
     Equation
    -0.88
    POSITIVE LOGITS
    favorite
    1.38
     ever
    1.24
     parmi
    1.20
     favorite
    1.16
     micrófono
    1.15
     myself
    1.08
     והוא
    1.05
    ]),
    1.05
     favoris
    1.05
     favourite
    1.05
    Activations Density 0.024%

    No Known Activations