© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31272
    Prev
    Next
    INDEX
    Explanations

    company registration and technical tutorials

    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
     qualifying
    -0.69
     Anaheim
    -0.67
     serum
    -0.66
    صیل
    -0.66
    issances
    -0.65
    naires
    -0.65
    ễn
    -0.64
    globin
    -0.64
     Hurricane
    -0.63
     Microbiol
    -0.63
    POSITIVE LOGITS
    🪨
    0.79
    traversal
    0.71
     Silvia
    0.71
     Traveler
    0.70
     venezuela
    0.68
     Marten
    0.66
    étaro
    0.66
    Phal
    0.66
     ATTR
    0.65
    解
    0.65
    Activations Density 0.056%

    No Known Activations