© 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. 6882
    Prev
    Next
    INDEX
    Explanations

    performance metrics and risks

    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
    ませ
    2.49
     পারেনা
    2.35
    Ѳ
    2.35
    堯
    2.29
    setClass
    2.25
    OU
    2.23
    TODO
    2.22
    ্
    2.20
    ways
    2.19
    ⋙
    2.15
    POSITIVE LOGITS
    𝐚
    2.51
    𝐨
    2.46
    pere
    2.33
    𝐞
    2.27
    س
    2.23
    𝐬
    2.22
     fgets
    2.21
    𝐩
    2.18
    ibalsan
    2.17
    ᡠ
    2.15
    Activations Density 0.413%

    No Known Activations