© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4794
    Prev
    Next
    INDEX
    Explanations

    Maya

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    otechnical
    0.85
    ceptron
    0.78
    郝
    0.78
     ultr
    0.76
    екст
    0.76
     Biosciences
    0.75
     rétro
    0.75
    coprotein
    0.75
     informatique
    0.75
    𝑓
    0.74
    POSITIVE LOGITS
     Maya
    1.60
    Maya
    1.52
     MAY
    1.34
     Mays
    1.32
    May
    1.30
    MAY
    1.30
    VA
    1.28
    Ay
    1.27
    MA
    1.23
     May
    1.22
    Activations Density 0.024%

    No Known Activations