© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    kind of

    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
    <bos>
    3.12
    kish
    2.79
     parties
    2.64
    parties
    2.55
    랄
    2.54
    īgi
    2.51
    ęb
    2.51
    umbing
    2.46
    ИА
    2.45
    ся
    2.38
    POSITIVE LOGITS
    ยนตร์
    2.87
    Literal
    2.52
    )|$(
    2.38
    eket
    2.37
    
    2.36
    Muchas
    2.34
    deleteAll
    2.33
    Clip
    2.33
    Servlet
    2.28
     parabol
    2.24
    Activations Density 0.388%

    No Known Activations