© 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. 629
    Prev
    Next
    INDEX
    Explanations

    Decided month

    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
     into
    -0.78
     action
    -0.74
    dbury
    -0.68
     Cory
    -0.68
    nicht
    -0.66
    рики
    -0.65
     RPG
    -0.65
     Action
    -0.65
    Cory
    -0.63
    rpm
    -0.62
    POSITIVE LOGITS
     bounces
    0.73
     GAC
    0.70
     Bounce
    0.70
     Sali
    0.69
     Transc
    0.68
     Novice
    0.68
     eletrônico
    0.67
     Liked
    0.66
    ιος
    0.66
    親子
    0.65
    Activations Density 0.059%

    No Known Activations