© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    bootstrap, link, dog, nesting, writing

    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
    
    2.22
    
    2.20
    c
    2.18
    
    2.17
    
    2.16
     nudge
    2.14
    𝓽
    2.09
    m
    2.09
    v
    2.08
     invari
    2.04
    POSITIVE LOGITS
     kõige
    2.21
    ele
    2.08
    ه
    2.07
     kobiet
    1.98
     아마
    1.98
    elem
    1.95
    amaan
    1.94
    ayv
    1.94
     mitä
    1.92
    মানা
    1.92
    Activations Density 0.019%

    No Known Activations