© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212913
    Prev
    Next
    INDEX
    Explanations

    harmful societal expectations

    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
    PAD
    0.40
    靝
    0.39
    chrift
    0.37
    臘
    0.36
    鬏
    0.36
    坫
    0.35
     Helena
    0.35
    Essex
    0.34
    Gambar
    0.34
    🌦
    0.34
    POSITIVE LOGITS
    suite
    0.45
    мато
    0.45
    спользование
    0.42
     фо
    0.42
     anhydride
    0.42
     complexity
    0.41
     compless
    0.40
     futuro
    0.40
    сар
    0.39
     будущее
    0.39
    Activations Density 0.005%

    No Known Activations