© 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. 47826
    Prev
    Next
    INDEX
    Explanations

    Explains and describes complexity

    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
     a
    0.53
     jargon
    0.52
     name
    0.51
     malware
    0.51
    NAMEN
    0.50
     nomi
    0.50
     fintech
    0.50
     be
    0.48
     angina
    0.48
     an
    0.48
    POSITIVE LOGITS
    我觉得
    0.54
     считаю
    0.53
    ㇇
    0.45
    ю
    0.45
    reel
    0.44
    我相信
    0.44
    我认为
    0.44
    リーグ
    0.42
    见过
    0.42
     xử
    0.42
    Activations Density 0.015%

    No Known Activations