© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    entirely and completely

    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
     merito
    0.91
     tejidos
    0.83
    捗
    0.80
     Bana
    0.80
    umo
    0.78
     चमक
    0.77
    rité
    0.77
    }/${
    0.75
    }:${
    0.74
    MCA
    0.74
    POSITIVE LOGITS
     altogether
    3.46
     entirely
    2.80
     вовсе
    2.61
     completely
    2.32
     вообще
    2.26
     totally
    2.15
     wholly
    2.11
     outright
    2.06
     Altogether
    2.01
     utterly
    1.99
    Activations Density 0.505%

    No Known Activations