© 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. 92701
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    STM
    -0.77
     стекло
    -0.77
    强制
    -0.75
     ordf
    -0.73
     begy
    -0.73
     gerne
    -0.71
     />\
    -0.70
     نهر
    -0.69
    nterior
    -0.69
     }_{\
    -0.69
    POSITIVE LOGITS
     Filip
    0.76
    سباب
    0.75
    Filip
    0.75
     carousel
    0.75
    ıca
    0.75
     mortgagee
    0.74
     chuyện
    0.73
    Sonder
    0.73
    mixin
    0.71
    Savage
    0.71
    Activations Density 0.006%

    No Known Activations