© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 556
    Prev
    Next
    INDEX
    Explanations

    numbers or dates

    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
     Twenty
    -1.55
     twenty
    -1.40
    Twenty
    -1.24
     Thirty
    -1.19
     Seventeen
    -1.13
     sixteen
    -1.09
     seventeen
    -1.06
     thirty
    -1.01
     Sixteen
    -1.01
     fifteen
    -0.96
    POSITIVE LOGITS
    ۱۱
    1.15
     ۱۱
    1.13
    ۱۰
    1.02
     tenth
    1.01
     ninth
    0.94
     ۱۲
    0.94
    ۱۲
    0.91
    9
    0.91
    eleven
    0.89
     XI
    0.88
    Activations Density 0.188%

    No Known Activations