© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 499
    Prev
    Next
    INDEX
    Explanations

    is mere or located

    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
     existentes
    0.30
     নিয়ত
    0.27
    ీయ
    0.27
     jeweil
    0.26
    ៗ
    0.26
     প্রবৃত্ত
    0.26
    ğlu
    0.25
     dipende
    0.25
    يهم
    0.25
    꿨
    0.24
    POSITIVE LOGITS
     certainly
    1.08
     definitely
    1.00
     probably
    0.95
     actually
    0.81
     certamente
    0.80
     undoubtedly
    0.79
     interesting
    0.79
     obviously
    0.79
    probably
    0.78
     admittedly
    0.78
    Activations Density 1.135%

    No Known Activations