© 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. 10-GEMMASCOPE-RES-131K
    7. 20023
    Prev
    Next
    INDEX
    Explanations

    factorial sequence notation

    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
    before
    -1.78
    𝑂
    -1.65
    vió
    -1.59
    蟜
    -1.53
    ᵢ
    -1.52
    🧐
    -1.51
    岀
    -1.51
     frenos
    -1.51
     ドラゴン
    -1.50
    tact
    -1.49
    POSITIVE LOGITS
    0
    1.78
     of
    1.67
     your
    1.49
    の世界
    1.45
     Since
    1.44
     esetben
    1.41
     Although
    1.37
     decreases
    1.35
     people
    1.35
     on
    1.35
    Activations Density 0.008%

    No Known Activations