© 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-65K
    7. 3274
    Prev
    Next
    INDEX
    Explanations

    demonym followed by associated noun

    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_65k_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
    ال
    0.49
    al
    0.48
    ul
    0.48
    ak
    0.47
    the
    0.46
    ج
    0.45
    la
    0.44
    تش
    0.42
    ना
    0.42
    x
    0.42
    POSITIVE LOGITS
     lawmakers
    0.47
     universities
    0.47
     psyche
    0.46
     culture
    0.45
     newspapers
    0.43
     хора
    0.41
     cuisine
    0.40
     människor
    0.40
     organs
    0.39
     famílias
    0.39
    Activations Density 0.100%

    No Known Activations