© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    Nylon, NVIDIA, N2O, narrator

    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
     Що
    0.94
     نیشنل
    0.91
    너
    0.90
    бал
    0.90
    NATIONAL
    0.89
     National
    0.88
    ᾗ
    0.87
     தண்ணீர்
    0.87
    水を
    0.85
    ἦ
    0.85
    POSITIVE LOGITS
    槃
    1.15
    clature
    1.15
    
    1.14
    ূনতম
    1.06
    ッシング
    1.05
    aisu
    1.01
    UTRAL
    1.01
    ativ
    1.00
    uaire
    0.99
    ineties
    0.99
    Activations Density 1.139%

    No Known Activations