© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106389
    Prev
    Next
    INDEX
    Explanations

    doctor, pregnant, feeding, practices

    np_acts-logits-general · gemini-2.5-flash-lite

    grooming behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     resistenza
    0.51
     trei
    0.50
     ricordare
    0.50
    詹
    0.49
    Salman
    0.48
     pojav
    0.48
    🚕
    0.47
    テスト
    0.46
    取締役
    0.46
     aggiungere
    0.46
    POSITIVE LOGITS
    ise
    0.47
    adeso
    0.46
     Letting
    0.45
    ²/
    0.45
    ianos
    0.44
    л
    0.44
    áns
    0.43
    ined
    0.42
    óf
    0.42
    äger
    0.42
    Activations Density 0.001%

    No Known Activations