© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21015
    Prev
    Next
    INDEX
    Explanations

    electron shells and orbits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     单位
    0.46
    र्ख
    0.44
     rebranded
    0.44
    Webhook
    0.43
    িণী
    0.43
    🍹
    0.43
    టికి
    0.42
     viande
    0.42
    醪
    0.42
     жидко
    0.41
    POSITIVE LOGITS
     orbitals
    1.37
     orbital
    1.27
     electron
    1.19
    orbital
    1.18
     electrons
    1.16
     orbits
    1.13
    electrons
    1.11
     orbit
    1.10
     Orbital
    1.10
     Electrons
    1.09
    Activations Density 0.019%

    No Known Activations