© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 591
    Prev
    Next
    INDEX
    Explanations

    new features and announcements

    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
     then
    -2.13
     such
    -1.80
     as
    -1.59
     his
    -1.52
     with
    -1.45
     or
    -1.42
     about
    -1.42
     aceptación
    -1.38
     certain
    -1.37
    più
    -1.36
    POSITIVE LOGITS
     imprim
    1.43
     Torneo
    1.34
     corred
    1.31
     precedente
    1.30
     Unidad
    1.28
     cubano
    1.27
     Capitán
    1.26
    ureusement
    1.25
     Occidente
    1.25
     Corazón
    1.24
    Activations Density 0.863%

    No Known Activations