© 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. 40656
    Prev
    Next
    INDEX
    Explanations

    Jupiter and Saturn

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

    planet Jupiter and gas giants

    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
     вулка
    0.44
     রক
    0.43
    星球
    0.43
    科學
    0.42
     أل
    0.41
    ву
    0.41
    🔈
    0.40
     সূ
    0.40
     स्पीकर
    0.40
     राख
    0.40
    POSITIVE LOGITS
    Jupiter
    0.46
     Juno
    0.45
     Jupiter
    0.43
    jupiter
    0.43
     Jov
    0.41
     swallowing
    0.40
     rapproche
    0.38
     bribery
    0.38
    lodge
    0.38
     choppy
    0.38
    Activations Density 0.018%

    No Known Activations