© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     if
    -1.79
    .
    -1.76
    معلومات
    -1.63
     péché
    -1.59
    </h3>
    -1.50
     plancher
    -1.48
    Otros
    -1.44
    Even
    -1.41
    Другие
    -1.40
     could
    -1.39
    POSITIVE LOGITS
    ...,
    1.65
     gorgeous
    1.65
     June
    1.61
     called
    1.55
    नलोड
    1.55
    <.
    1.55
     ardent
    1.52
     namorados
    1.52
    centiles
    1.52
    ൎ
    1.51
    Activations Density 0.005%

    No Known Activations