© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6560
    Prev
    Next
    INDEX
    Explanations

    legal issues and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    睐
    0.40
    らう
    0.38
    怎么办
    0.36
    做一个
    0.36
     reinvent
    0.35
     gemak
    0.35
     makeover
    0.35
    的感觉
    0.35
    パートナー
    0.34
     irresist
    0.34
    POSITIVE LOGITS
     ಮತ್ತು
    0.37
     અને
    0.36
    owel
    0.35
    лению
    0.34
     (_
    0.33
     ਅਤੇ
    0.33
    دة
    0.33
    known
    0.33
     ligados
    0.32
    ление
    0.31
    Activations Density 0.001%

    No Known Activations