© 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. 119792
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
    どういう
    -1.78
     a
    -1.72
     MUCH
    -1.63
     feiert
    -1.49
    进入了
    -1.47
    </h4>
    -1.46
     isolado
    -1.45
     tomado
    -1.42
     STUDENTS
    -1.41
    来到了
    -1.40
    POSITIVE LOGITS
     or
    2.36
     after
    1.71
     of
    1.48
    or
    1.45
    任何
    1.36
     any
    1.33
    This
    1.31
    這
    1.31
     gdyż
    1.30
    skapet
    1.27
    Activations Density 0.012%

    No Known Activations