© 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. 67300
    Prev
    Next
    INDEX
    Explanations

    greeting or question word

    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
    9
    -1.36
    8
    -1.17
    呖
    -1.11
    4
    -1.08
    3
    -1.08
    October
    -1.07
    M
    -1.06
    ༈
    -1.05
     disheart
    -1.05
    $
    -1.04
    POSITIVE LOGITS
    Sqft
    1.14
     and
    1.09
    したのは
    1.08
     EVERYTHING
    0.99
     but
    0.98
    ~!
    0.98
     Distrikt
    0.97
     lámparas
    0.97
     κάνει
    0.96
     algodón
    0.94
    Activations Density 0.141%

    No Known Activations