© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107986
    Prev
    Next
    INDEX
    Explanations

    aggressive testosterone behavior

    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
    ני
    0.46
    ﻮ
    0.39
    ަ
    0.39
     회사
    0.39
    SA
    0.38
     येणार
    0.38
    URO
    0.38
    ুয়ারি
    0.37
    وه
    0.37
    נה
    0.37
    POSITIVE LOGITS
     aperto
    0.47
    胀
    0.43
     ligne
    0.41
     मछली
    0.41
     dard
    0.40
     горя
    0.40
     못
    0.39
     imparted
    0.39
     éclair
    0.39
    лении
    0.39
    Activations Density 0.003%

    No Known Activations