© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10182
    Prev
    Next
    INDEX
    Explanations

    translate something from

    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_13_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
    𝐥
    1.80
     evoking
    1.67
    widths
    1.67
    𝐧
    1.64
    𝐭
    1.58
    lh
    1.57
    𝐨
    1.53
    𝐚
    1.53
    𝐡
    1.52
    allowing
    1.51
    POSITIVE LOGITS
    WithDictionary
    1.28
    ERRE
    1.21
    ICLES
    1.20
     बलि
    1.19
    ForEach
    1.17
     غادي
    1.15
    MainMenu
    1.15
    에
    1.14
     consenso
    1.13
     nhiêu
    1.13
    Activations Density 0.003%

    No Known Activations