© 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. 22-GEMMASCOPE-RES-131K
    7. 73851
    Prev
    Next
    INDEX
    Explanations

    introducing details or explanations

    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_22/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
     erheblich
    -1.26
    j
    -1.22
     dando
    -1.21
     breathtaking
    -1.20
     caractéris
    -1.18
     fazendo
    -1.17
     nostra
    -1.17
     ib
    -1.15
     erstmal
    -1.15
     drei
    -1.14
    POSITIVE LOGITS
     of
    1.91
     which
    1.82
     regarding
    1.58
     barna
    1.48
     when
    1.46
     kommunik
    1.43
     również
    1.41
     that
    1.36
     with
    1.35
    Tentang
    1.33
    Activations Density 0.020%

    No Known Activations