© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16005
    Prev
    Next
    INDEX
    Explanations

    summation and accumulation

    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_22/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
    conic
    -0.84
    幽默
    -0.82
    tiglie
    -0.80
     percent
    -0.74
     細
    -0.74
    uvres
    -0.73
    xac
    -0.73
    羊肉
    -0.73
    section
    -0.72
    epik
    -0.72
    POSITIVE LOGITS
     sum
    1.14
    čeno
    0.96
     مجموع
    0.93
     cumulative
    0.92
    cumulative
    0.89
    Cumulative
    0.87
     totalling
    0.87
    SUM
    0.87
    checksum
    0.86
     summation
    0.86
    Activations Density 0.057%

    No Known Activations