© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143390
    Prev
    Next
    INDEX
    Explanations

    adverse conditions or something protected

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

    preserving asset / melting ice

    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
    ు
    0.56
    ্ল
    0.48
    ভারতীয়
    0.47
     स्वभाव
    0.46
     ዕ
    0.46
     объект
    0.45
    ис
    0.45
     onscreen
    0.44
    c
    0.44
    лок
    0.43
    POSITIVE LOGITS
     kalo
    0.50
     ma
    0.48
     kalau
    0.48
     ponad
    0.47
     Senator
    0.44
     Prize
    0.44
     Forum
    0.44
    または
    0.44
     o
    0.43
     \$
    0.43
    Activations Density 0.000%

    No Known Activations