© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2104
    Prev
    Next
    INDEX
    Explanations

    calling functions

    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
    ה
    3.31
    BURGH
    2.36
    ब्ल्यू
    2.31
     skinned
    2.30
     stepped
    2.29
    ophenone
    2.29
    hesians
    2.26
    ۰
    2.25
    ი
    2.24
    NUMX
    2.23
    POSITIVE LOGITS
    𝐥
    2.52
    𝐚
    2.24
    ্লা
    2.20
    𝐢
    2.19
    𝐮
    2.18
    ings
    2.13
    ز
    2.11
    𝐲
    2.09
    لت
    2.08
    uar
    2.06
    Activations Density 0.049%

    No Known Activations