© 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. 93576
    Prev
    Next
    INDEX
    Explanations

    future material models and burglars

    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
     although
    -1.04
    …？
    -0.92
     with
    -0.91
     when
    -0.91
     both
    -0.91
     not
    -0.90
    ؤال
    -0.90
    ・・。
    -0.89
    ongeza
    -0.83
    fino
    -0.82
    POSITIVE LOGITS
    ۵
    0.96
    Ivan
    0.94
     pagrind
    0.90
    ٦
    0.87
     почему
    0.87
     बदल
    0.87
     Navidad
    0.86
                               
    0.86
     लाभ
    0.86
    ≥
    0.85
    Activations Density 0.011%

    No Known Activations