© 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. 21670
    Prev
    Next
    INDEX
    Explanations

    OK, None, ReadOnly

    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
     each
    -1.49
    什么样的
    -1.48
     consideran
    -1.33
    ApJ
    -1.28
     elizabeth
    -1.27
     图案
    -1.27
     explications
    -1.22
     jugo
    -1.21
    Benzene
    -1.20
    POSITIVE LOGITS
     but
    1.48
     podremos
    1.46
     tendremos
    1.41
    hezza
    1.38
     see
    1.30
     option
    1.30
    ="
    1.28
    போ
    1.27
     &
    1.27
    áveis
    1.26
    Activations Density 0.087%

    No Known Activations