© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1365
    Prev
    Next
    INDEX
    Explanations

    states and changes

    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_17_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
     நன்ற
    0.89
    庥
    0.86
     非常
    0.84
     breve
    0.82
     тему
    0.81
     tremend
    0.78
     সমগ্র
    0.78
    ELINE
    0.77
    
    0.77
    દિવસ
    0.77
    POSITIVE LOGITS
     according
    4.28
    according
    3.97
     selon
    3.48
     According
    3.38
    According
    3.38
     menurut
    3.32
     según
    3.31
     volgens
    3.20
     enligt
    2.99
     σύμφωνα
    2.88
    Activations Density 1.040%

    No Known Activations