© 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. 123635
    Prev
    Next
    INDEX
    Explanations

    of attributes, thereof which

    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
     amerikanischen
    -1.25
     after
    -1.24
     when
    -1.20
     marginLeft
    -1.16
     Jugendlichen
    -1.15
    /*
    -1.15
     that
    -1.15
     milioane
    -1.13
     põ
    -1.12
     appropriately
    -1.11
    POSITIVE LOGITS
     who
    1.35
    🗣
    1.31
     funktion
    1.30
    stof
    1.26
     the
    1.26
    namn
    1.25
    tainable
    1.24
     sinds
    1.22
     SOON
    1.21
     {
    1.20
    Activations Density 0.082%

    No Known Activations