© 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. 549
    Prev
    Next
    INDEX
    Explanations

    BETWEEN and ZERO

    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
     heeft
    1.00
    的作用
    0.91
     सच्ची
    0.87
     proporciona
    0.86
    ләр
    0.85
     bietet
    0.85
    是
    0.85
     предоставляет
    0.84
    และ
    0.84
     în
    0.84
    POSITIVE LOGITS
    ther
    0.89
    zig
    0.78
    ⃣
    0.74
    ter
    0.73
     রকম
    0.72
    𝐟
    0.72
    vent
    0.72
    Rs
    0.71
    stm
    0.69
    teen
    0.68
    Activations Density 0.537%

    No Known Activations