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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112253
    Prev
    Next
    INDEX
    Explanations

    ED, APA, EUR

    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
    =@"
    -1.31
    ↵
    -1.26
     tény
    -1.25
     creando
    -1.24
    río
    -1.18
    kadi
    -1.15
     realmente
    -1.15
     generando
    -1.13
     considerados
    -1.12
     Leaf
    -1.11
    POSITIVE LOGITS
     a
    1.36
     then
    1.30
    不断的
    1.29
    费用
    1.27
    r
    1.23
     minori
    1.19
     demander
    1.16
     poils
    1.16
    at
    1.13
     different
    1.13
    Activations Density 0.047%

    No Known Activations