© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 206571
    Prev
    Next
    INDEX
    Explanations

    your noun phrases

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

    actions and states of being like recording and owning

    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
     ㅅ
    0.54
     проблем
    0.49
     vět
    0.48
     gamanam
    0.48
    spaceBetween
    0.48
     좋
    0.47
    "})
    0.47
     sebelum
    0.47
    velocityY
    0.46
     பிரச்சன
    0.46
    POSITIVE LOGITS
     
    0.53
    دت
    0.52
    س
    0.49
    اري
    0.49
    اسي
    0.48
    الس
    0.48
    تس
    0.47
    ال
    0.47
    Dg
    0.46
    انيه
    0.45
    Activations Density 0.001%

    No Known Activations