© 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. 62393
    Prev
    Next
    INDEX
    Explanations

    Magnetic response

    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
    Negative Logits
     gire
    -0.78
    カン
    -0.74
     roh
    -0.73
     fråga
    -0.70
     Sess
    -0.69
     quis
    -0.69
    manufact
    -0.69
    HAW
    -0.69
    ensas
    -0.68
    Disclosures
    -0.68
    POSITIVE LOGITS
    msb
    0.93
    MSB
    0.80
     projekt
    0.79
    GetResponse
    0.79
     Condition
    0.76
     MS
    0.75
     Property
    0.75
     Magal
    0.74
    Sdk
    0.74
     hipote
    0.74
    Activations Density 0.077%

    No Known Activations