© 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. 10-GEMMASCOPE-RES-131K
    7. 41706
    Prev
    Next
    INDEX
    Explanations

    Sports and technology events

    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
     Saltar
    -1.69
    ┖
    -1.63
    INTAIN
    -1.62
     indivíduo
    -1.59
     destacó
    -1.59
    说实话
    -1.55
    渽
    -1.52
     ANCHE
    -1.48
    再度
    -1.44
     sostuvo
    -1.44
    POSITIVE LOGITS
    stech
    1.43
    潜力
    1.42
    lardan
    1.42
     oraz
    1.35
    ORPG
    1.34
    nitř
    1.30
     \#
    1.27
    mäßigen
    1.25
     —
    1.24
    额头
    1.24
    Activations Density 0.045%

    No Known Activations