© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3584
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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
    年始
    2.93
    isas
    2.76
    ص
    2.63
     Cached
    2.60
    uptools
    2.54
    =’
    2.48
    目录下
    2.48
    حصل
    2.42
    主义
    2.41
    ອກ
    2.38
    POSITIVE LOGITS
    राधिक
    3.40
    躇
    3.19
    𝐇
    3.12
    \%.
    3.06
    "।
    3.02
    \&
    3.02
    ."[
    2.99
    methylsulfanyl
    2.92
    seat
    2.91
    .",
    2.89
    Activations Density 0.318%

    No Known Activations