© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73611
    Prev
    Next
    INDEX
    Explanations

    an article followed by a noun

    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
    Recently
    -1.38
    ibrill
    -1.35
     erwähnten
    -1.34
    Approximately
    -1.25
     Occasionally
    -1.25
     erlä
    -1.23
     Некоторые
    -1.21
    訁
    -1.21
    architecte
    -1.20
     надпись
    -1.19
    POSITIVE LOGITS
     this
    1.41
    łby
    1.40
     why
    1.38
     correa
    1.30
     tudo
    1.30
     (
    1.29
    (
    1.27
    >
    1.27
     or
    1.25
     todos
    1.23
    Activations Density 0.079%

    No Known Activations