© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    data mining and related algorithms

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms and concepts related to data mining, algorithms, and computational analysis.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     portuguesa
    -1.20
    fokus
    -1.16
    igem
    -1.13
     siquiera
    -1.09
     tarifa
    -1.09
    parken
    -1.09
    鹩
    -1.08
    y
    -1.05
    umpulkan
    -1.03
     caricatura
    -1.03
    POSITIVE LOGITS
     like
    1.26
     for
    1.23
     todėl
    1.15
    åde
    1.09
    liques
    1.09
     tačiau
    1.09
    función
    1.05
     bienfaits
    1.02
    聴いて
    1.02
    偎
    1.01
    Activations Density 0.050%

    No Known Activations