© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128482
    Prev
    Next
    INDEX
    Explanations

    wavelength, spectral, spectrum

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

    scientific concepts related to light, wavelength, and spectral analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hébergement
    -1.52
     établissement
    -1.23
    ּוֹ
    -1.20
     kirke
    -1.16
     zwei
    -1.14
    通常
    -1.14
    PyObject
    -1.13
     echte
    -1.11
     heeft
    -1.09
    PositiveButton
    -1.09
    POSITIVE LOGITS
     that
    1.48
    ῖν
    1.25
     Amritsar
    1.18
     showing
    1.17
    цца
    1.16
    很赞
    1.13
    引用元
    1.11
    　↓
    1.10
    ρούν
    1.10
     Grosso
    1.09
    Activations Density 0.012%

    No Known Activations