© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    etymology and science 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_7_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
    ي
    3.31
    न
    3.15
    ture
    3.09
    rī
    3.02
    يلا
    2.99
    י
    2.97
    tale
    2.93
    ്യ
    2.93
    র
    2.89
    م
    2.85
    POSITIVE LOGITS
    𝔪
    2.43
     garde
    2.18
    วม
    2.17
     make
    2.14
    俬
    2.11
     вдруг
    2.10
    )(=
    2.10
    chr
    2.08
    довж
    2.07
     evolve
    2.05
    Activations Density 0.019%

    No Known Activations