© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65055
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
     only
    -1.09
     dolar
    -1.00
     some
    -0.97
     all
    -0.96
     know
    -0.96
     ONLY
    -0.96
     JUST
    -0.92
     asas
    -0.91
    ิ่น
    -0.90
     just
    -0.88
    POSITIVE LOGITS
     último
    1.01
    兩種
    0.96
    ujący
    0.94
    another
    0.88
     rzeczyw
    0.86
     solucionar
    0.84
     鸭
    0.84
     percent
    0.84
     선택
    0.83
     aceasta
    0.82
    Activations Density 0.023%

    No Known Activations