© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118749
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
    퐹
    -2.06
     afectadas
    -1.86
    '].'
    -1.85
    DEAN
    -1.81
     exigencias
    -1.79
     recomand
    -1.77
    zijn
    -1.77
     verksam
    -1.75
     conductas
    -1.73
    AKB
    -1.73
    POSITIVE LOGITS
     it
    2.81
     then
    2.55
     they
    2.41
     you
    2.36
    ?
    2.16
    {
    2.14
     there
    2.13
    9
    2.00
     when
    1.99
     would
    1.89
    Activations Density 0.414%

    No Known Activations