© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    visual + descriptive

    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
    𝒂
    2.47
    𝒓
    2.45
    𝒐
    2.39
    quilibrium
    2.36
    ილები
    2.19
    —“
    2.17
    𝒄
    2.17
    ঞ্জেল
    2.17
    𝒊
    2.14
    𝒆
    2.10
    POSITIVE LOGITS
    ㇂
    2.98
    囪
    2.94
    ից
    2.71
    缭
    2.50
     izme
    2.36
    <bos>
    2.34
     кла
    2.33
     unat
    2.33
    ゚
    2.32
    ਿੰ
    2.28
    Activations Density 0.920%

    No Known Activations