© 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. 22-GEMMASCOPE-RES-131K
    4. 9614
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
     sooo
    -2.09
     vijf
    -2.09
     astounding
    -2.05
     soooo
    -2.03
     amazingly
    -1.94
     Quando
    -1.88
     astonishing
    -1.87
     cinq
    -1.87
     joyous
    -1.84
     molte
    -1.80
    POSITIVE LOGITS
     from
    2.52
     by
    2.27
     with
    2.22
     while
    2.20
     at
    2.06
     if
    1.99
     first
    1.98
     regardless
    1.98
     for
    1.97
     through
    1.97
    Activations Density 0.023%

    No Known Activations