© 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. 13-GEMMASCOPE-2-RES-65K
    7. 150
    Prev
    Next
    INDEX
    Explanations

    mathematical sqrt operations

    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_65k_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
     more
    0.80
    .
    0.77
     More
    0.77
    '
    0.76
     k
    0.68
    More
    0.68
     with
    0.67
     even
    0.65
    k
    0.65
     K
    0.64
    POSITIVE LOGITS
    ⮚
    1.40
    apetva
    1.36
     kehnd
    1.34
     iccad
    1.32
     BSData
    1.31
    <unused398>
    1.30
    BUUID
    1.30
     dhinak
    1.30
    𒍣
    1.28
    <unused1952>
    1.28
    Activations Density 0.000%

    No Known Activations