© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30320
    Prev
    Next
    INDEX
    Explanations

    empty stomach

    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_all/layer_41_width_262k_l0_big
    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
     pouss
    0.44
    ParamNum
    0.42
     legales
    0.39
     legalized
    0.39
     equitable
    0.38
     legalize
    0.38
    詷
    0.37
     دام
    0.37
     शह
    0.36
     giurid
    0.36
    POSITIVE LOGITS
     fasting
    1.61
     fasted
    1.52
     empty
    1.30
     Empty
    1.27
    空
    1.27
    empty
    1.24
    Empty
    1.19
     EMPTY
    1.04
    EMPTY
    0.99
    空的
    0.98
    Activations Density 0.004%

    No Known Activations