© 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. 56141
    Prev
    Next
    INDEX
    Explanations

    definition, growth, brain, Jumia

    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
     Keine
    0.53
    ध्यात्म
    0.50
    僟
    0.50
    雒
    0.49
    baikan
    0.47
    屣
    0.47
    iftet
    0.46
    लेकिन
    0.45
    娠
    0.45
    igamma
    0.45
    POSITIVE LOGITS
     tam
    0.43
    ]])
    0.42
     drank
    0.41
     ra
    0.40
     arterial
    0.40
     می‌کنند
    0.40
     ox
    0.39
     paraphernalia
    0.39
     کر
    0.39
     salty
    0.39
    Activations Density 0.019%

    No Known Activations