© 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. 16923
    Prev
    Next
    INDEX
    Explanations

    spectroscopy spectral features and emission

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

    spectral absorption and emission

    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
     финансо
    0.65
     демокра
    0.65
    祸
    0.63
     Марафон
    0.62
     gön
    0.62
    绩效
    0.59
     جیتنے
    0.59
    समाज
    0.59
    驿
    0.59
    谲
    0.59
    POSITIVE LOGITS
     spectral
    0.99
     spectra
    0.95
     spectroscopy
    0.88
     spectroscopic
    0.79
     emission
    0.78
    spectral
    0.76
     absorption
    0.75
    spectra
    0.75
     spectrum
    0.73
     spectrosc
    0.70
    Activations Density 0.029%

    No Known Activations