© 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. 176858
    Prev
    Next
    INDEX
    Explanations

    liable for, safeguarding your, mortar joints

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

    savings rate

    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
     イヤ
    0.62
     ある
    0.54
     після
    0.54
     ܗ
    0.52
     антен
    0.52
     シル
    0.51
     scienza
    0.50
     осві
    0.49
     ըն
    0.49
     gehörte
    0.49
    POSITIVE LOGITS
    '
    0.52
    up
    0.52
    alcohol
    0.51
    Nice
    0.50
     Nice
    0.49
     Beds
    0.46
    omy
    0.46
    that
    0.46
    it
    0.46
    ewall
    0.46
    Activations Density 0.001%

    No Known Activations