© 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. 30167
    Prev
    Next
    INDEX
    Explanations

    learning retention

    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
    ähig
    -0.96
    🧼
    -0.86
    ροσ
    -0.85
    EXIST
    -0.81
     Hồ
    -0.79
    žete
    -0.79
     佛
    -0.78
    ataire
    -0.78
    HEE
    -0.78
    möglichkeiten
    -0.77
    POSITIVE LOGITS
     retention
    2.58
     retain
    2.08
     Retention
    2.05
    Retention
    2.03
     retained
    1.88
    retention
    1.88
     retaining
    1.86
    Retain
    1.74
     reinforce
    1.70
     reinforcement
    1.70
    Activations Density 0.033%

    No Known Activations