© 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. 79437
    Prev
    Next
    INDEX
    Explanations

    mangosMangosMangomangosmangosmangosmangosmangomangosmangosmangos

    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
     masculine
    -0.83
     masculinity
    -0.81
    σουμε
    -0.77
    poids
    -0.75
     endlich
    -0.75
    裁
    -0.75
     каждого
    -0.74
    nnn
    -0.74
    男性
    -0.72
     fijar
    -0.71
    POSITIVE LOGITS
     Mang
    0.84
    Mang
    0.81
     Cela
    0.78
     exquisitely
    0.75
     mang
    0.75
     disastrous
    0.74
     saison
    0.74
     grá
    0.73
    sandalias
    0.73
    Benef
    0.73
    Activations Density 0.012%

    No Known Activations