© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44224
    Prev
    Next
    INDEX
    Explanations

    continue or remain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -1.71
     presumably
    -1.35
     скорее
    -1.32
     Kedua
    -1.28
    istered
    -1.27
    i
    -1.27
    hdessä
    -1.26
     with
    -1.25
    вість
    -1.25
    住所
    -1.23
    POSITIVE LOGITS
     doivent
    1.66
     bő
    1.59
    weiterlesen
    1.55
    一脸
    1.55
    ドキドキ
    1.43
    ᥬ
    1.38
    remains
    1.38
    represents
    1.36
     müh
    1.34
     우리
    1.34
    Activations Density 0.052%

    No Known Activations