© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14762
    Prev
    Next
    INDEX
    Explanations

    cost savings and efficiency

    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_7_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
    uah
    1.28
    gue
    1.22
     (
    1.13
    nt
    1.12
    id
    1.11
    is
    1.11
    udel
    1.10
    seid
    1.10
    ęp
    1.08
    se
    1.06
    POSITIVE LOGITS
    <unused1344>
    1.98
     वैलेंट
    1.82
    SubDirectoryPath
    1.80
    <unused1334>
    1.78
    <unused1502>
    1.77
    <unused1394>
    1.77
    <unused1393>
    1.76
    <unused1467>
    1.75
    <unused1288>
    1.75
    <unused1427>
    1.74
    Activations Density 0.034%

    No Known Activations