© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32201
    Prev
    Next
    INDEX
    Explanations

    mask and region segmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assertArray
    -0.76
    zeniu
    -0.75
    ccional
    -0.73
     Serbie
    -0.69
     相談
    -0.68
    шими
    -0.68
    جات
    -0.68
    ikus
    -0.67
     typo
    -0.67
    cek
    -0.67
    POSITIVE LOGITS
     mask
    1.88
    Mask
    1.66
     masks
    1.63
     Mask
    1.54
    mask
    1.53
    MASK
    1.49
    Masks
    1.38
     masking
    1.37
     Masks
    1.31
     MASK
    1.31
    Activations Density 0.047%

    No Known Activations