© 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. 69643
    Prev
    Next
    INDEX
    Explanations

    whatever followed by a condition

    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
     who
    -1.64
     wasn
    -1.59
     Tonnen
    -1.48
     like
    -1.45
    的是
    -1.41
     nhat
    -1.40
     couldn
    -1.37
     is
    -1.34
     today
    -1.34
     are
    -1.32
    POSITIVE LOGITS
    formatie
    1.45
    孳
    1.42
     animados
    1.41
     kült
    1.40
    »?
    1.38
    侷
    1.38
     gwaran
    1.37
     vientos
    1.37
     essayer
    1.35
     origins
    1.34
    Activations Density 0.014%

    No Known Activations