© 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. 62365
    Prev
    Next
    INDEX
    Explanations

    Anna

    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
    エアコン
    -0.91
     NASH
    -0.85
     朝食
    -0.84
     metropolitana
    -0.81
     cittad
    -0.79
    ころ
    -0.78
     chiare
    -0.77
     democra
    -0.77
     churrasco
    -0.76
    ibration
    -0.76
    POSITIVE LOGITS
    belle
    1.56
    bel
    1.38
     Maria
    1.24
    Maria
    1.18
     Anna
    1.13
    pur
    1.11
     Marie
    1.02
    бель
    0.99
    Anna
    0.98
    ées
    0.93
    Activations Density 0.007%

    No Known Activations