© 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. 130143
    Prev
    Next
    INDEX
    Explanations

    online edition and particular pattern

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

    youtube-dl, DNA strand, odd locations, future opportunities, casual sex

    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
    T
    0.54
    B
    0.47
    $}
    0.46
    cc
    0.45
    verick
    0.44
    L
    0.43
    ovich
    0.43
    <0xAB>
    0.42
    G
    0.42
    ]
    0.42
    POSITIVE LOGITS
    사의
    0.58
    Соцмережа
    0.56
     സോ
    0.55
    龌
    0.55
     lymphatiques
    0.54
     smears
    0.52
    ເພື່ອ
    0.51
     vortices
    0.50
    라고
    0.50
    𝙢
    0.50
    Activations Density 0.001%

    No Known Activations