© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16494
    Prev
    Next
    INDEX
    Explanations

    AI/ML, code, fiction

    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
    と
    0.51
     અને
    0.47
    とその
    0.46
     и
    0.46
     ಮತ್ತು
    0.45
    тери
    0.44
    𝗯
    0.44
     ਅਤੇ
    0.43
     और
    0.42
    及び
    0.42
    POSITIVE LOGITS
    :
    0.47
     ganz
    0.42
    ;
    0.42
     zei
    0.41
     righteousness
    0.41
     wichtig
    0.40
     جیسا
    0.40
     voisinage
    0.40
     kuten
    0.39
     vergangenen
    0.39
    Activations Density 0.016%

    No Known Activations