© 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. 125022
    Prev
    Next
    INDEX
    Explanations

    percentages of

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

    concepts for an audience

    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
     begon
    0.58
    anium
    0.54
     byg
    0.52
    ƅ
    0.48
    łow
    0.48
     Kasım
    0.48
     koszt
    0.46
    ilize
    0.46
    ł
    0.46
     bekerja
    0.46
    POSITIVE LOGITS
     سي
    0.46
    ানে
    0.46
     ين
    0.45
    άν
    0.44
    াহি
    0.44
    وي
    0.43
     {
    0.41
    اني
    0.41
    該
    0.41
     هي
    0.41
    Activations Density 0.001%

    No Known Activations