© 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. 1571
    Prev
    Next
    INDEX
    Explanations

    referring to or defining terms

    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
    namen
    0.87
    수에
    0.87
    =*
    0.86
    足够
    0.85
    bufs
    0.84
    毎
    0.83
    肯定是
    0.81
    ]==
    0.79
    heng
    0.78
    ettamente
    0.78
    POSITIVE LOGITS
     known
    2.08
    known
    2.06
    Known
    1.78
     Known
    1.77
     popularly
    1.75
     conocida
    1.74
     affectionately
    1.73
     aka
    1.70
     conocido
    1.69
     conocidos
    1.68
    Activations Density 0.185%

    No Known Activations