© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    engineering and technical concepts

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

    challenges and solutions in AI

    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
     cocker
    0.54
     revest
    0.53
    ⠈
    0.53
     unmist
    0.52
     unequiv
    0.51
     heartache
    0.51
    ㄍ
    0.51
     saff
    0.51
    砧
    0.51
     lineal
    0.50
    POSITIVE LOGITS
     computationally
    0.89
     trivially
    0.85
     architectures
    0.84
     instantiated
    0.83
     QoS
    0.83
     instantiation
    0.80
    Computational
    0.77
    ~\
    0.76
    ~(
    0.76
     Computational
    0.76
    Activations Density 0.143%

    No Known Activations