© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79242
    Prev
    Next
    INDEX
    Explanations

    forge, blacksmith, ironwork

    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
     stitched
    -0.78
    ઇ
    -0.77
    getMock
    -0.76
    ('&
    -0.74
    ohjel
    -0.74
     sats
    -0.73
    🦡
    -0.73
     Sein
    -0.73
    writing
    -0.73
     cardboard
    -0.73
    POSITIVE LOGITS
     forge
    2.38
     blacksmith
    2.17
     forging
    2.05
    forge
    1.98
     Forge
    1.91
    Forge
    1.85
     smith
    1.78
     iron
    1.78
     anvil
    1.64
     furnace
    1.59
    Activations Density 0.018%

    No Known Activations