© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    introduction to a breakdown

    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
     абсолютно
    0.70
     erg
    0.69
     nw
    0.68
     oxford
    0.66
    দিকে
    0.66
     bt
    0.66
    合格
    0.65
    宜
    0.64
    nox
    0.64
     দেখে
    0.63
    POSITIVE LOGITS
    Ꮝ
    1.17
     Eel
    1.15
     Clément
    1.09
     йөк
    1.05
     될
    1.03
     Fett
    1.03
    صير
    1.02
     Jésus
    1.01
    auft
    1.01
    FileLine
    1.01
    Activations Density 0.055%

    No Known Activations