© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92507
    Prev
    Next
    INDEX
    Explanations

    to AGM sent create

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

    why questions and explanations

    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
    Negative Logits
     پرته
    0.53
    asshi
    0.51
     தன்னை
    0.48
     সাঁ
    0.47
     ভাষার
    0.46
     নামটি
    0.46
     பகுதியை
    0.46
     भाषा
    0.46
     indipendente
    0.46
    𒊭
    0.46
    POSITIVE LOGITS
     In
    0.47
     oxide
    0.47
     Alkaline
    0.47
     CL
    0.46
     glycoprotein
    0.46
     ablaze
    0.44
     Corrosion
    0.43
     Cur
    0.42
     sermon
    0.42
     GCP
    0.42
    Activations Density 0.001%

    No Known Activations