© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3586
    Prev
    Next
    INDEX
    Explanations

    rural areas communities

    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
    ContentView
    2.36
    aint
    2.03
     Sum
    1.98
    𝙩
    1.95
    ൃശ
    1.94
    hemat
    1.91
    aper
    1.91
    elu
    1.90
    立
    1.86
     Up
    1.85
    POSITIVE LOGITS
     indexBuffer
    2.66
    ಯಲ್ಲಿ
    2.60
    sset
    2.54
    s
    2.53
    nG
    2.53
    ση
    2.51
    ಯ
    2.48
     πολύ
    2.48
    schnitt
    2.47
    ים
    2.45
    Activations Density 0.067%

    No Known Activations