© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4294
    Prev
    Next
    INDEX
    Explanations

    mac or mc followed by various words

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝜇
    0.41
    టి
    0.41
     précisément
    0.41
    akoti
    0.40
    လျှ
    0.40
    šanu
    0.40
    BlockFit
    0.38
     afect
    0.38
    ^*(
    0.37
    GBuf
    0.37
    POSITIVE LOGITS
     mac
    0.95
     Mac
    0.91
     맥
    0.86
     OSX
    0.84
    Mac
    0.84
     MAC
    0.83
    mac
    0.82
    intosh
    0.80
     Macbeth
    0.75
     मैक
    0.75
    Activations Density 0.044%

    No Known Activations