© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1228
    Prev
    Next
    INDEX
    Explanations

    making informed decisions

    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
     to
    -1.55
     که
    -1.34
     {
    -1.31
     {'
    -1.22
     что
    -1.16
    𝟒
    -1.16
    %;
    
    -1.15
    metology
    -1.14
    isMethod
    -1.14
    いかが
    -1.14
    POSITIVE LOGITS
    0
    1.31
     hesit
    1.30
     on
    1.27
     competir
    1.22
    шать
    1.20
     بشأن
    1.20
     impulsar
    1.17
     and
    1.16
    </em>
    1.16
     hinzufügen
    1.15
    Activations Density 0.067%

    No Known Activations