© 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. 850
    Prev
    Next
    INDEX
    Explanations

    ebook title placeholder

    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
    aties
    0.97
     saith
    0.95
    важа
    0.94
    ':
    0.93
    或其他
    0.91
    :-
    0.90
    ’:
    0.90
    ່າງ
    0.90
    ”:
    0.90
    或是
    0.89
    POSITIVE LOGITS
     referencing
    1.31
     summing
    1.27
     referring
    1.26
     wry
    1.21
     summarizing
    1.19
     gesturing
    1.16
     launching
    1.15
     adding
    1.14
     assessing
    1.12
    quoting
    1.08
    Activations Density 0.180%

    No Known Activations