© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151713
    Prev
    Next
    INDEX
    Explanations

    size, numbers, and specifications

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

    no direct attacks

    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_31_width_262k_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
     Hamiltonian
    0.49
     viciss
    0.48
     Але
    0.47
    olim
    0.46
     Preferably
    0.45
     Много
    0.44
     "
    0.44
     seme
    0.43
     lý
    0.43
     περί
    0.43
    POSITIVE LOGITS
    krank
    0.45
    ק
    0.44
     međ
    0.43
    _,
    0.42
    iob
    0.42
    ষ্ঠ
    0.41
    BySize
    0.41
    श्
    0.41
    ಿನಿ
    0.41
     معادله
    0.41
    Activations Density 0.000%

    No Known Activations