© 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. 123559
    Prev
    Next
    INDEX
    Explanations

    suddenly became

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

    manual troubleshooting

    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
     however
    0.47
     your
    0.43
     but
    0.43
     will
    0.43
     однако
    0.42
     buts
    0.42
    ↵
    0.42
    があるので
    0.42
     optio
    0.42
     bonito
    0.41
    POSITIVE LOGITS
    纡
    0.48
     본격
    0.46
     ঘোষণার
    0.46
     മുഖ്യമ
    0.44
     plötzlich
    0.44
    деги
    0.44
    ığımızda
    0.43
    ດ້ວຍ
    0.43
     devenu
    0.42
     شفنا
    0.42
    Activations Density 0.002%

    No Known Activations