© 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. 34-GEMMASCOPE-RES-131K
    7. 47965
    Prev
    Next
    INDEX
    Explanations

    deprecated code comments

    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_34/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
     UNDER
    -0.75
    сомо
    -0.72
     Anlagen
    -0.68
    glUniform
    -0.67
     regulations
    -0.67
    வர
    -0.66
     under
    -0.65
     RELATED
    -0.64
     Scrip
    -0.63
     wizards
    -0.63
    POSITIVE LOGITS
    ponge
    0.78
     passiert
    0.67
     Jensen
    0.66
     طور
    0.65
    aram
    0.65
    arri
    0.65
    Nop
    0.64
     Neves
    0.64
    ապ
    0.64
     پذ
    0.64
    Activations Density 0.059%

    No Known Activations