© 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. 104661
    Prev
    Next
    INDEX
    Explanations

    chance to win prizes

    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
    ("")){
    -1.62
     mocno
    -1.37
    to
    -1.34
    In
    -1.29
     dłu
    -1.27
     проблему
    -1.24
     relevant
    -1.23
    』『
    -1.22
    弍
    -1.20
    琑
    -1.20
    POSITIVE LOGITS
     a
    1.32
    ління
    1.32
    ってました
    1.29
    pięk
    1.26
    pakah
    1.26
    Eucalyptus
    1.25
    PLAUSE
    1.24
     caracter
    1.23
     оказался
    1.23
    不高
    1.22
    Activations Density 0.029%

    No Known Activations