© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10944
    Prev
    Next
    INDEX
    Explanations

    astronomy and astrophysics

    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_31_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
    哐
    0.59
    蝈
    0.59
    忘记
    0.56
    焦虑
    0.56
    粿
    0.55
    嘞
    0.55
     التمرين
    0.54
    违反
    0.53
    萆
    0.53
    善良
    0.53
    POSITIVE LOGITS
     astronomers
    1.46
     astronomer
    1.27
     astronomy
    1.25
     astrophysical
    1.25
     galactic
    1.19
     Astronom
    1.16
     astrophys
    1.15
     astronomical
    1.14
     interstellar
    1.14
     Astronomy
    1.13
    Activations Density 0.056%

    No Known Activations