© 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. 27366
    Prev
    Next
    INDEX
    Explanations

    sorting by name or column

    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
     मुझसे
    0.37
     εξ
    0.36
    setDescription
    0.35
    埋
    0.35
    emment
    0.35
    荞
    0.34
     আমেরিকা
    0.34
    词
    0.34
    бли
    0.34
    aliers
    0.34
    POSITIVE LOGITS
     పార్టీ
    0.43
     ដើម្បី
    0.42
    ÍN
    0.42
    ULL
    0.41
     கட்ச
    0.41
     Kombination
    0.40
     tehát
    0.40
     Party
    0.40
    ný
    0.40
    INO
    0.40
    Activations Density 0.086%

    No Known Activations