© 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. 6285
    Prev
    Next
    INDEX
    Explanations

    encourage and discourage

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

    encouragement

    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
     menjelaskan
    0.58
     storied
    0.57
    ’,
    0.56
    ะ
    0.56
     महाभारत
    0.54
     दट
    0.53
     HAVE
    0.52
     fungsi
    0.52
     aturan
    0.52
    ă
    0.52
    POSITIVE LOGITS
     Encour
    1.20
     encouragement
    1.17
    encour
    1.11
     discouraged
    1.10
    鼓励
    1.05
     encour
    1.02
     discour
    1.00
     encouraging
    0.97
     encourage
    0.96
     encouraged
    0.95
    Activations Density 0.055%

    No Known Activations