© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3669
    Prev
    Next
    INDEX
    Explanations

    government urls

    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
    𝐥
    2.99
    𝚜
    2.62
    𝐬
    2.55
    𝐧
    2.52
    љу
    2.42
    𝐭
    2.42
    互联网档案馆
    2.40
    Rés
    2.38
    Mong
    2.34
    ,\,\
    2.32
    POSITIVE LOGITS
    s
    3.92
    ات
    3.02
    いる
    2.94
    sons
    2.55
    ுள்ள
    2.46
    ς
    2.37
    sess
    2.35
    sher
    2.29
    ़
    2.28
    t
    2.26
    Activations Density 0.052%

    No Known Activations