© 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. 118017
    Prev
    Next
    INDEX
    Explanations

    x86 assembly intrinsics

    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
    ocyan
    -0.82
     dur
    -0.75
     grandparents
    -0.73
     *$
    -0.73
    NEAR
    -0.70
    ЙТЕ
    -0.68
    مپ
    -0.67
    iap
    -0.66
    Ax
    -0.66
    我已经
    -0.66
    POSITIVE LOGITS
     ffs
    1.32
     population
    1.28
    ffs
    1.22
    population
    1.16
    Population
    1.14
     Population
    1.09
     pop
    1.06
    pop
    0.99
     populations
    0.99
     count
    0.96
    Activations Density 0.054%

    No Known Activations