© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7263
    Prev
    Next
    INDEX
    Explanations

    number of / equivalent amount

    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_31_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
    ５
    0.53
    棰
    0.53
    耶
    0.52
    кін
    0.52
    琊
    0.51
     двох
    0.50
    WebApi
    0.49
     Streak
    0.49
     बनाती
    0.48
    锜
    0.48
    POSITIVE LOGITS
    $...
    0.59
    បន្ថ
    0.58
     blindness
    0.56
    evenly
    0.56
    ertain
    0.54
    ప్పుడు
    0.54
     TInner
    0.53
    adden
    0.52
     넓
    0.52
    }}=-\
    0.52
    Activations Density 0.001%

    No Known Activations