© 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. 177210
    Prev
    Next
    INDEX
    Explanations

    earning points

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

    months and abstract concepts

    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
    ওয়্যার
    0.53
     міся
    0.52
     创建
    0.51
     ゆっくり
    0.51
     リビング
    0.51
     механизм
    0.51
    вати
    0.50
     肌
    0.50
    <unused1003>
    0.50
    <unused1060>
    0.50
    POSITIVE LOGITS
     June
    0.50
     onscreen
    0.50
    June
    0.48
    October
    0.46
    Rob
    0.43
    ا
    0.43
    Am
    0.41
     December
    0.41
     graham
    0.41
    بعة
    0.41
    Activations Density 0.001%

    No Known Activations