© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    Ruhen lassen, photons, Aquaponics

    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
     imageView
    3.16
    짖
    2.91
     अभिव्यक्ति
    2.85
     लिखा
    2.83
    ോഷ്യ
    2.83
    外观
    2.83
    ório
    2.79
    ocols
    2.79
    вать
    2.75
     calibrations
    2.74
    POSITIVE LOGITS
    아가
    2.88
    에
    2.67
    加坡
    2.50
     ương
    2.48
     (...
    2.29
     '(
    2.22
    en
    2.22
    oje
    2.21
    '
    2.17
    م
    2.17
    Activations Density 0.005%

    No Known Activations