© 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. 11618
    Prev
    Next
    INDEX
    Explanations

    ambient air signal

    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
     çünkü
    -2.06
     this
    -1.70
    啐
    -1.59
    peinture
    -1.51
    〢
    -1.45
    bestos
    -1.44
     interesantes
    -1.38
    меча
    -1.36
     edifício
    -1.34
     their
    -1.34
    POSITIVE LOGITS
     but
    1.75
     didn
    1.68
    焐
    1.66
     aforementioned
    1.60
    当时
    1.54
    躄
    1.53
     mentioned
    1.52
     or
    1.44
     prior
    1.41
     previously
    1.36
    Activations Density 0.146%

    No Known Activations