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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14803
    Prev
    Next
    INDEX
    Explanations

    ISO performance

    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
    域
    2.33
    ben
    2.18
     cae
    2.14
     ac
    2.12
    acr
    2.07
     <!--
    2.04
    ac
    2.03
     \<
    2.02
     frem
    2.01
    vcn
    2.01
    POSITIVE LOGITS
    𝙧
    2.77
    𝙡
    2.64
    𝙩
    2.62
    𝙙
    2.55
     نفسك
    2.33
    ಿಗ
    2.33
    cephalus
    2.29
    咙
    2.29
    𝙜
    2.28
    𝙠
    2.28
    Activations Density 0.001%

    No Known Activations