© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
     지난해
    0.82
     노
    0.79
    oğlu
    0.76
     일으
    0.75
    生效
    0.75
    ੰ
    0.75
    мет
    0.75
    ਤਰ
    0.75
    更多
    0.73
    _{*
    0.72
    POSITIVE LOGITS
     configure
    0.72
     charm
    0.71
     preach
    0.69
     configuração
    0.66
     obsessed
    0.65
     gratuit
    0.64
     indulge
    0.63
     disseminate
    0.63
     begyn
    0.63
     charming
    0.63
    Activations Density 0.086%

    No Known Activations