© 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. 50765
    Prev
    Next
    INDEX
    Explanations

    brothers and sisters

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

    start of revolutions

    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
    δου
    0.45
    Δ
    0.44
     prints
    0.44
     shades
    0.42
     dazz
    0.41
    库
    0.41
     infidelity
    0.41
    丧
    0.41
     intoler
    0.40
     enclosures
    0.40
    POSITIVE LOGITS
    pei
    0.49
     Criticism
    0.48
     STEELS
    0.46
    䙲
    0.46
     முய
    0.45
    叧
    0.45
     GRAPH
    0.45
     တော့
    0.45
    䡋
    0.45
     BOOKS
    0.45
    Activations Density 0.000%

    No Known Activations