© 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. 66058
    Prev
    Next
    INDEX
    Explanations

    rake task commands

    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
    d
    -3.03
     However
    -2.92
     Importantly
    -2.83
     Significantly
    -2.64
     With
    -2.58
     But
    -2.48
     Therefore
    -2.47
     Slightly
    -2.45
     Notably
    -2.44
     That
    -2.39
    POSITIVE LOGITS
     første
    2.33
     provocando
    2.19
     étudier
    2.16
     fantástica
    2.16
     realizando
    2.14
     maravillosa
    2.14
    cisive
    2.13
     rst
    2.11
     czarny
    2.00
     største
    2.00
    Activations Density 0.005%

    No Known Activations