© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    the word while

    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
    ordinate
    2.35
    igny
    2.28
    дцать
    2.21
    ፧
    2.15
    ља
    2.13
    цией
    2.12
    ኋላ
    2.08
    atoren
    2.05
    руя
    2.05
    、“
    2.04
    POSITIVE LOGITS
    ៉
    2.60
    搬型
    2.57
    borist
    2.46
    gı
    2.37
    Ziel
    2.33
    මාන්
    2.32
     oblic
    2.29
    ંપ
    2.28
     woon
    2.27
    ે
    2.22
    Activations Density 0.276%

    No Known Activations