© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6603
    Prev
    Next
    INDEX
    Explanations

    first translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused227>
    0.35
     waitUntil
    0.35
    之间的
    0.34
    ContentAlignment
    0.34
    的其他
    0.34
    atterson
    0.33
    \%).
    0.32
    酱
    0.32
    <unused426>
    0.32
    spacerItem
    0.32
    POSITIVE LOGITS
     pertama
    0.73
     first
    0.72
     eerste
    0.71
     पहला
    0.69
     erste
    0.68
     primeiro
    0.68
     첫
    0.66
     erstes
    0.66
     primeira
    0.65
    第一個
    0.63
    Activations Density 1.148%

    No Known Activations