© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9442
    Prev
    Next
    INDEX
    Explanations

    expressing a wish or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ριο
    0.95
    rischen
    0.87
    듀
    0.86
    秀
    0.85
    ورو
    0.85
    atur
    0.84
     regal
    0.83
     डीएल
    0.83
     teles
    0.80
    瑠
    0.80
    POSITIVE LOGITS
     réponse
    1.33
     risposta
    1.32
     respuesta
    1.31
     response
    1.28
    response
    1.26
     resposta
    1.21
     responses
    1.20
     answers
    1.16
     reply
    1.15
     answer
    1.15
    Activations Density 0.295%

    No Known Activations