© 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-65K
    7. 955
    Prev
    Next
    INDEX
    Explanations

    sounds and tactile sensations

    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_65k_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
     Marriage
    1.07
    Marriage
    1.06
     yaşında
    1.06
    áról
    1.04
    債
    1.02
    สนับสนุน
    1.00
    Geme
    0.98
     rozší
    0.98
     solidaridad
    0.95
     Merger
    0.94
    POSITIVE LOGITS
    睡觉
    1.29
     bedtime
    1.13
     утром
    1.07
     fidget
    1.05
     asleep
    1.04
     寝
    1.03
     lotion
    1.02
    睡
    1.00
    饭
    1.00
     exerting
    0.98
    Activations Density 1.386%

    No Known Activations