© 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. 106284
    Prev
    Next
    INDEX
    Explanations

    for standardization

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

    phrases ending in "II"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    etis
    0.45
     Demons
    0.44
    و
    0.43
    計劃
    0.43
    }
    0.43
    rinos
    0.42
    aris
    0.41
    weights
    0.41
    jima
    0.41
    এছাড়া
    0.41
    POSITIVE LOGITS
     cobran
    0.53
     पासवर्ड
    0.45
     संदिग्ध
    0.45
    <0x80>
    0.43
    必ず
    0.43
    俱乐
    0.43
     managerial
    0.43
     男女
    0.43
    Amsterdam
    0.43
     empec
    0.43
    Activations Density 0.001%

    No Known Activations