© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    open/closed times and states

    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
     menggunakan
    -1.76
     walaupun
    -1.52
    vages
    -1.40
     decât
    -1.36
     meskipun
    -1.35
     portatil
    -1.34
     esigen
    -1.34
     rezultat
    -1.32
     koment
    -1.31
     zima
    -1.30
    POSITIVE LOGITS
     (
    1.71
     an
    1.42
     innumerable
    1.31
    これらの
    1.29
     A
    1.24
     „
    1.20
     this
    1.19
     hours
    1.19
     endearing
    1.16
    ()
    1.16
    Activations Density 0.029%

    No Known Activations