© 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. 106652
    Prev
    Next
    INDEX
    Explanations

    JavaScript language usage

    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
     alemán
    -0.84
     allemand
    -0.81
    Jury
    -0.81
     la
    -0.80
    メラ
    -0.79
    Bleeding
    -0.78
     sua
    -0.77
     sumptuous
    -0.77
     hauling
    -0.76
    Geen
    -0.76
    POSITIVE LOGITS
     jsi
    1.11
    Executor
    1.09
     kuku
    0.94
     believes
    0.90
    quity
    0.87
    EventLoop
    0.86
    }}</
    0.86
     VALOR
    0.86
     kya
    0.86
     jaja
    0.85
    Activations Density 0.076%

    No Known Activations