© 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. 127533
    Prev
    Next
    INDEX
    Explanations

    settlement

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

    cost alternatives

    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
    练
    0.57
    세
    0.57
    家
    0.55
    田
    0.55
    온
    0.54
    и
    0.53
    ⵢ
    0.52
    利
    0.51
    车
    0.51
    约
    0.50
    POSITIVE LOGITS
     crystallinity
    0.50
     (€
    0.50
     viscose
    0.50
     quartzite
    0.48
     paraffin
    0.48
     huwa
    0.48
     silicate
    0.48
     softmax
    0.47
     dù
    0.46
     monolithic
    0.46
    Activations Density 0.000%

    No Known Activations