© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    generally followed by assessment

    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
    ي
    1.20
    ی
    1.16
    ệm
    1.11
    ี
    1.06
    ์
    1.03
    й
    1.03
    u
    1.03
    स्तिक
    1.02
    ம்
    1.02
    ную
    0.98
    POSITIVE LOGITS
    :\\
    1.26
    ));//
    1.25
    ,\\
    1.24
    )}=
    1.17
    델
    1.16
     harness
    1.16
     फेस्टिव
    1.15
    ίνη
    1.14
     [{'
    1.12
    ,【
    1.12
    Activations Density 0.075%

    No Known Activations