© 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. 40-GEMMASCOPE-2-RES-262K
    4. 13807
    Prev
    Next
    INDEX
    Explanations

    Mazda cars

    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_40_width_262k_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
    鄧
    0.46
    PerTrial
    0.44
     Chev
    0.43
    ittäin
    0.42
    獃
    0.42
     userID
    0.41
     কর্
    0.41
    koľ
    0.40
     katılı
    0.40
    /')
    0.40
    POSITIVE LOGITS
    Maz
    0.98
     Mazda
    0.96
     Maz
    0.89
     maz
    0.85
     Hiroshima
    0.76
    maz
    0.72
     CX
    0.67
     Sky
    0.60
    cx
    0.60
     SKY
    0.60
    Activations Density 0.004%

    No Known Activations