© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23565
    Prev
    Next
    INDEX
    Explanations

    to him or his

    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
    sizeof
    0.36
     flake
    0.36
    abcdef
    0.36
    rna
    0.36
    parents
    0.34
    >();
    0.34
    sheet
    0.34
     sheet
    0.34
     clothes
    0.33
    萑
    0.33
    POSITIVE LOGITS
     him
    0.82
    這位
    0.78
    这位
    0.73
    后者
    0.67
    前者
    0.61
     нём
    0.58
     ihn
    0.57
     njega
    0.54
     lui
    0.53
     ним
    0.53
    Activations Density 0.005%

    No Known Activations