© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5336
    Prev
    Next
    INDEX
    Explanations

    Baton Rouge, Khmer Rouge, Paris-Roubaix

    np_acts-logits-general · gemini-2.5-flash-lite

    Bernoulli, Cotonou, Alamouti, stdout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    性价比
    0.54
     ав
    0.54
    🦯
    0.45
     lineColorSpace
    0.45
    ✲
    0.43
    ின்றன
    0.43
    aeskeygenassist
    0.43
     पन
    0.42
     переписи
    0.41
    磐
    0.41
    POSITIVE LOGITS
    ou
    2.48
     Lou
    2.47
     Kou
    2.47
    OU
    2.44
     kou
    2.36
    Lou
    2.34
     Bou
    2.33
    kou
    2.33
    bou
    2.30
    Bou
    2.27
    Activations Density 0.204%

    No Known Activations