© 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. 22-GEMMASCOPE-RES-131K
    7. 12418
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes or modifying phrases

    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_22/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
     Catawiki
    -1.00
    нути
    -0.99
    gives
    -0.88
     Penang
    -0.87
    它
    -0.86
    tit
    -0.85
    它的
    -0.84
     VOID
    -0.84
    throws
    -0.82
    ROSE
    -0.82
    POSITIVE LOGITS
     into
    0.87
     by
    0.85
     through
    0.81
     incorporated
    0.81
     If
    0.80
    =<?
    0.80
     reflected
    0.78
    interopRequire
    0.77
     before
    0.77
     disimpan
    0.76
    Activations Density 0.106%

    No Known Activations