© 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. 57279
    Prev
    Next
    INDEX
    Explanations

    ethnicities and cultures

    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
     altri
    0.48
     IQR
    0.45
     titer
    0.44
     راجسټریشن
    0.43
    ினேன்
    0.42
     गह
    0.42
     sebagainya
    0.41
     ރ
    0.41
    ">'
    0.41
     aptly
    0.41
    POSITIVE LOGITS
    Mal
    0.56
    Gym
    0.52
    Ethnic
    0.52
    Electric
    0.49
    Man
    0.48
    Desc
    0.48
    izações
    0.48
    Рабо
    0.48
    Play
    0.47
    Phosph
    0.47
    Activations Density 0.000%

    No Known Activations