© 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. 63921
    Prev
    Next
    INDEX
    Explanations

    license terms

    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
    insk
    -0.91
    :{
    -0.89
    ";
    -0.89
    문
    -0.88
    VolleyError
    -0.88
     their
    -0.88
     she
    -0.87
    >+</
    -0.86
    ֔
    -0.85
    ()){
    -0.85
    POSITIVE LOGITS
     aktiviteter
    1.20
    imarães
    1.06
     やすい
    1.01
    してしまう
    0.94
    angun
    0.93
     aktivitet
    0.93
     그것
    0.92
     defy
    0.91
     egenskaper
    0.90
    ondissement
    0.90
    Activations Density 0.226%

    No Known Activations