© 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. 13284
    Prev
    Next
    INDEX
    Explanations

    access and accrue

    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
    cystic
    2.68
    ષ્ઠ
    2.59
    azaki
    2.49
    紝
    2.48
    ingly
    2.41
    adhan
    2.41
    tog
    2.38
    ative
    2.36
     enteric
    2.33
    য়ার
    2.30
    POSITIVE LOGITS
    ние
    2.70
    िनेट
    2.66
    𝘩
    2.66
    헛
    2.65
    FirstResponder
    2.55
    عه
    2.54
    िपल
    2.53
    팍
    2.50
    نامه
    2.49
    eket
    2.45
    Activations Density 0.006%

    No Known Activations