© 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. 34-GEMMASCOPE-RES-131K
    7. 77677
    Prev
    Next
    INDEX
    Explanations

    first item

    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_34/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
    inerario
    -1.52
    なかな
    -1.48
     relentless
    -1.42
    凄く
    -1.42
    割と
    -1.41
    ヤバ
    -1.39
    凄い
    -1.38
    色んな
    -1.34
    何と
    -1.34
     remarkably
    -1.33
    POSITIVE LOGITS
     two
    3.02
     three
    2.25
     four
    1.73
     few
    1.60
     of
    1.58
     one
    1.51
     five
    1.50
     couple
    1.41
    两个
    1.29
    三个
    1.28
    Activations Density 0.090%

    No Known Activations