© 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. 13741
    Prev
    Next
    INDEX
    Explanations

    bracketed placeholders for names

    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
    s
    4.16
    ted
    3.12
    t
    2.89
    teles
    2.83
    tang
    2.80
    tra
    2.70
    getSystemService
    2.69
    nya
    2.64
    tem
    2.61
    self
    2.59
    POSITIVE LOGITS
    𝑟
    2.98
    atac
    2.96
    рана
    2.88
    рь
    2.87
    𝐫
    2.81
    𝑏
    2.76
    𝑤
    2.74
     coveredmethods
    2.71
    𝑑
    2.71
    LevelLinking
    2.69
    Activations Density 0.010%

    No Known Activations