© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    dependent variable

    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
    ו
    4.22
    a
    3.95
    i
    3.91
    ه
    3.68
    o
    3.42
    る
    3.33
    ר
    3.29
    an
    3.24
    า
    3.22
    ात
    3.18
    POSITIVE LOGITS
    स्तिष्क
    2.47
    ей
    2.33
    proving
    2.27
    ຍ
    2.24
    HING
    2.23
    ज
    2.23
    ⿱
    2.21
    ্ভব
    2.20
    ष्णु
    2.20
     propriedade
    2.19
    Activations Density 0.001%

    No Known Activations