© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    youtube watch links

    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
     والغ
    1.85
     Punishment
    1.80
     وتح
    1.77
    并且
    1.74
     и
    1.74
     وتق
    1.73
     但是
    1.71
     و
    1.70
     或者
    1.69
     και
    1.67
    POSITIVE LOGITS
     namesake
    1.74
    picode
    1.66
    जलवायु
    1.54
    bibfield
    1.54
    cvec
    1.54
    icel
    1.53
    ვალ
    1.52
    eqref
    1.51
     bevy
    1.47
    panorama
    1.47
    Activations Density 0.512%

    No Known Activations