© 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. 18237
    Prev
    Next
    INDEX
    Explanations

    judging others or making decisions

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

    judging

    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
     carbohydrate
    0.64
     infrastrukt
    0.62
     disrupt
    0.58
     disprove
    0.55
     subway
    0.55
    क्सीडेंट
    0.54
     nitrile
    0.53
     u
    0.53
    t
    0.52
    tà
    0.52
    POSITIVE LOGITS
     judgement
    1.26
     judgements
    1.25
    judgment
    1.22
     judgment
    1.20
     judgments
    1.17
     Decisions
    1.15
     decisión
    1.14
    判定
    1.13
     jugement
    1.13
     판단
    1.13
    Activations Density 0.053%

    No Known Activations