© 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. 249827
    Prev
    Next
    INDEX
    Explanations

    massacre of, rid of, most of

    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
    Fond
    0.52
    第二百
    0.50
     Fondo
    0.50
    バランス
    0.50
     incre
    0.48
    हिंद
    0.46
    6
    0.46
    クレ
    0.45
     fondo
    0.45
    従業
    0.45
    POSITIVE LOGITS
    érés
    0.47
    ospheric
    0.46
     ရက်
    0.45
    olded
    0.43
    copied
    0.43
    letek
    0.43
    一旦
    0.43
    steroidal
    0.43
    osphere
    0.42
    énés
    0.42
    Activations Density 0.001%

    No Known Activations