© 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. 7-GEMMASCOPE-2-RES-16K
    4. 13080
    Prev
    Next
    INDEX
    Explanations

    a lot

    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
    ス
    1.42
    (
    1.33
     また
    1.30
    ర
    1.24
     However
    1.24
     This
    1.23
     If
    1.20
     บน
    1.19
    。(
    1.19
     rin
    1.17
    POSITIVE LOGITS
     gastronom
    1.65
     breakers
    1.50
     comfy
    1.48
    င့်
    1.48
     catered
    1.46
    趣
    1.45
     prerog
    1.43
    ⌞
    1.43
    DefineConstants
    1.41
    ̀
    1.41
    Activations Density 0.012%

    No Known Activations