© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13488
    Prev
    Next
    INDEX
    Explanations

    often, sometimes, usually

    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
    beleid
    -1.48
     folgt
    -1.41
     new
    -1.38
     atau
    -1.31
     not
    -1.29
     who
    -1.28
     niet
    -1.28
     ۱۳۹
    -1.26
    会の
    -1.25
     مختلف
    -1.17
    POSITIVE LOGITS
     geralmente
    1.52
    often
    1.36
    sometimes
    1.30
     poderão
    1.28
     outras
    1.24
     otros
    1.23
    usually
    1.22
     terão
    1.21
    probably
    1.20
     serão
    1.20
    Activations Density 0.234%

    No Known Activations