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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15682
    Prev
    Next
    INDEX
    Explanations

    **race** or gender

    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
     होने
    0.43
    ському
    0.40
    គ្ន
    0.40
    }_{-
    0.38
    трима
    0.37
     पेर
    0.37
    इसलिए
    0.37
     ഞങ്ങൾ
    0.37
    hoven
    0.37
     तैयारी
    0.37
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.43
     '''
    0.43
    یمی
    0.40
     jūs
    0.40
    '";
    0.39
    developer
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
     '(
    0.37
     evaded
    0.37
    USERS
    0.36
    Activations Density 0.000%

    No Known Activations