© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14097
    Prev
    Next
    INDEX
    Explanations

    mutable references in rust

    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
    蒡
    2.38
    cı
    2.36
     yaptık
    2.33
    Personensuche
    2.33
    затор
    2.30
     thoại
    2.29
    რც
    2.28
    زش
    2.24
    vich
    2.22
     appropriation
    2.22
    POSITIVE LOGITS
    ا
    2.97
    ᱽ
    2.37
     tomber
    2.37
    ේ
    2.37
    PLS
    2.32
     Hath
    2.26
    tyn
    2.24
    ের
    2.24
    راہیم
    2.23
    િંહ
    2.22
    Activations Density 0.012%

    No Known Activations