© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1029
    Prev
    Next
    INDEX
    Explanations

    multiple languages and punctuation

    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
    ↵↵
    2.01
    ↵↵↵
    1.60
    ↵↵↵↵
    1.48
    <start_of_image>
    1.38
    ↵↵↵↵↵↵
    1.37
    ↵↵↵↵↵
    1.33
    ‬‬
    1.24
    </h2>
    1.23
    ↵
    1.20
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.18
    POSITIVE LOGITS
    onek
    1.29
    okan
    1.12
    asem
    1.10
    daad
    1.09
    ucch
    1.09
    「
    1.08
    ...(
    1.08
    ujudkan
    1.07
    zechoslovak
    1.06
    ęk
    1.06
    Activations Density 0.022%

    No Known Activations