© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    define/redefine

    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
    гей
    0.84
    지
    0.79
    ITHER
    0.78
    ꯋ
    0.77
    อ
    0.77
    戞
    0.76
    ciri
    0.75
    지요
    0.75
    ो
    0.74
     노트북
    0.73
    POSITIVE LOGITS
     alve
    0.77
    тку
    0.71
    ational
    0.70
     attend
    0.67
     ambul
    0.67
     hydrate
    0.66
     Specialized
    0.66
    ুল
    0.65
     uv
    0.65
     noss
    0.65
    Activations Density 0.000%

    No Known Activations