© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9025
    Prev
    Next
    INDEX
    Explanations

    presenting something

    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
    ا
    2.69
    ات
    2.58
    ત્મ
    2.42
    اث
    2.39
    ̣c
    2.29
    اا
    2.25
    zak
    2.24
    טן
    2.19
     rspace
    2.17
    بن
    2.14
    POSITIVE LOGITS
    𝐬
    3.17
    𝐢
    2.97
    𝐡
    2.75
     drm
    2.75
    𝐝
    2.69
    stArray
    2.66
    𝐨
    2.65
    𝐞
    2.62
    ০০
    2.58
     ovale
    2.54
    Activations Density 0.348%

    No Known Activations