© 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. 10-GEMMASCOPE-RES-131K
    7. 8084
    Prev
    Next
    INDEX
    Explanations

    allocator and libc

    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_10/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
    阋
    -2.52
     rajut
    -2.52
    鮡
    -2.45
     transparan
    -2.44
    ꪔ
    -2.41
    鏐
    -2.38
    疍
    -2.38
     murah
    -2.36
     menyen
    -2.31
     brune
    -2.30
    POSITIVE LOGITS
     
    3.77
    </h1>
    3.20
      
    2.80
    "
    2.69
    </h3>
    2.59
     I
    2.50
     say
    2.25
     snug
    2.17
    」、「
    2.16
     _________
    2.09
    Activations Density 0.004%

    No Known Activations