© 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. 75119
    Prev
    Next
    INDEX
    Explanations

    couple of

    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
     kleines
    -2.08
     Zuschauer
    -2.05
    siswa
    -1.92
     geralmente
    -1.89
     größte
    -1.84
    ῞
    -1.80
    sä
    -1.80
     enchufe
    -1.73
     Überprüfung
    -1.73
     acoged
    -1.72
    POSITIVE LOGITS
    al
    2.86
     of
    2.27
    e
    1.95
     dozen
    1.73
    am
    1.59
    通过
    1.54
    山西
    1.54
    d
    1.52
    ◈
    1.49
    窠
    1.48
    Activations Density 0.007%

    No Known Activations