© 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. 47968
    Prev
    Next
    INDEX
    Explanations

    being back

    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
    Komple
    -1.55
    FORME
    -1.54
    Kontra
    -1.54
    hasilkan
    -1.51
    Cinta
    -1.48
     mikrofon
    -1.46
     what
    -1.46
     seksi
    -1.45
    』。
    -1.45
    ÖR
    -1.44
    POSITIVE LOGITS
    p
    1.54
    v
    1.46
    </h1>
    1.45
     #
    1.42
    w
    1.41
    I
    1.41
    j
    1.37
    x
    1.27
     to
    1.27
     in
    1.26
    Activations Density 0.021%

    No Known Activations