© 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. 66372
    Prev
    Next
    INDEX
    Explanations

    movie, ingredients, etc

    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
     hierbas
    -1.45
     doubtless
    -1.40
    /…
    -1.30
    ⁦
    -1.30
     hitherto
    -1.27
    訣
    -1.23
     PRAYER
    -1.23
     Tinggi
    -1.22
     ristoranti
    -1.22
     anlay
    -1.21
    POSITIVE LOGITS
     &
    1.66
     ->
    1.52
     <-
    1.42
     &&
    1.41
    ></
    1.39
     ponieważ
    1.38
     \\
    1.28
    んでる
    1.27
     explicó
    1.27
    즘
    1.26
    Activations Density 0.051%

    No Known Activations