Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14662
    Prev
    Next
    INDEX
    Explanations

    social stereotypes and objectification

    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
    垩
    0.42
    hu
    0.39
     недостаточно
    0.38
    ۃ
    0.37
    itie
    0.37
    chwitz
    0.36
     Núñez
    0.36
    ừa
    0.36
    ueless
    0.35
     Jawah
    0.35
    POSITIVE LOGITS
     obat
    0.43
    을
    0.40
    yaml
    0.38
     yaml
    0.37
     tato
    0.37
    ROOT
    0.36
    stdlib
    0.36
    ቛ
    0.35
    穵
    0.35
     desl
    0.35
    Activations Density 0.000%

    No Known Activations