© 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. 13-GEMMASCOPE-2-RES-16K
    4. 8573
    Prev
    Next
    INDEX
    Explanations

    even within or different

    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_13_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
    else
    1.20
    лює
    1.18
    ِل
    1.17
     иных
    1.15
    ildet
    1.15
    ící
    1.15
     प्रिय
    1.14
    懋
    1.13
    ímav
    1.13
    itative
    1.11
    POSITIVE LOGITS
     thru
    1.16
     通过
    1.12
     खोसला
    1.12
     tk
    1.12
     kou
    1.11
    ttu
    1.10
    soo
    1.10
     turnkey
    1.09
     shot
    1.08
     couples
    1.06
    Activations Density 0.000%

    No Known Activations