© 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. 13295
    Prev
    Next
    INDEX
    Explanations

    d followed by newline, quote, or comma

    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
     sales
    1.82
     Μαρ
    1.80
    ᆹ
    1.74
     care
    1.73
    idyl
    1.70
     sale
    1.67
    блон
    1.65
     preparing
    1.59
     (“
    1.59
     stol
    1.58
    POSITIVE LOGITS
    াকা
    2.34
    mok
    2.22
     شمار
    2.22
    sı
    2.21
    ោះស្រាយ
    2.19
    Num
    2.18
    幾個
    2.16
    栦
    2.16
     Num
    2.15
    numer
    2.13
    Activations Density 0.009%

    No Known Activations