© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6702
    Prev
    Next
    INDEX
    Explanations

    delimiter followed by your

    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
    চিতে
    1.26
     दिखाता
    1.19
     eventos
    1.18
    옇
    1.17
     cuộc
    1.13
     peristiwa
    1.12
     பிரச்
    1.11
     चक्रवृद्धि
    1.10
     kết
    1.10
    getEstado
    1.10
    POSITIVE LOGITS
     Lieblings
    0.94
     adored
    0.92
    wing
    0.91
     Descripción
    0.90
     Caff
    0.90
     promised
    0.89
    ’
    0.89
     Becoming
    0.88
     Everyday
    0.88
     Identity
    0.87
    Activations Density 0.005%

    No Known Activations