© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14926
    Prev
    Next
    INDEX
    Explanations

    of varying processes

    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
     শেখ
    1.51
     φο
    1.33
    adoo
    1.29
     phony
    1.26
     Slash
    1.24
     প্রেম
    1.23
     比
    1.23
     Eee
    1.22
     Ive
    1.21
     Buzz
    1.20
    POSITIVE LOGITS
    品質
    1.42
    いない
    1.37
    दीय
    1.32
    滿
    1.31
    يجي
    1.29
     jakości
    1.28
     نهایت
    1.26
    தந்திர
    1.25
    ודי
    1.22
     दक्षता
    1.21
    Activations Density 0.000%

    No Known Activations