© 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. 34-GEMMASCOPE-RES-131K
    7. 73335
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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_34/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
     and
    -1.21
    仨
    -1.11
    先前
    -1.10
    hésite
    -1.05
    ykjav
    -1.05
    有不
    -1.04
    ")
    -1.02
    ,:);
    -1.02
    ")
    -1.01
    скій
    -1.01
    POSITIVE LOGITS
    :
    5.13
    ：……
    1.97
    :[],
    1.55
    ：“……”
    1.44
     :
    1.41
    ：
    1.20
    ：「
    1.18
    :{
    1.15
    ：　
    1.13
    :"",
    1.10
    Activations Density 0.089%

    No Known Activations