© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1635
    Prev
    Next
    INDEX
    Explanations

    perhaps, please, conclusion

    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_17_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
     Etc
    0.95
    🥰
    0.92
     TikTok
    0.91
     Tiktok
    0.91
     Daarnaast
    0.90
     ასევე
    0.89
    yout
    0.88
     देखील
    0.87
    yrıca
    0.86
     सुद्धा
    0.85
    POSITIVE LOGITS
     --
    1.88
     —
    1.86
     ـ
    1.83
    ――
    1.76
    ——
    1.74
     –
    1.72
    .—
    1.71
     ——
    1.70
     (_
    1.61
    .–
    1.60
    Activations Density 0.368%

    No Known Activations