© 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. 93553
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols

    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
    localObject
    -0.69
     phospho
    -0.68
     Frey
    -0.67
     phylogeny
    -0.66
    Sites
    -0.66
    ohjel
    -0.66
    هات
    -0.65
    veloped
    -0.64
     IDENTIFICATION
    -0.63
    ometri
    -0.62
    POSITIVE LOGITS
     із
    0.67
     السنة
    0.66
    OrUpdate
    0.65
    ICTION
    0.65
    writeFieldEnd
    0.65
    気
    0.65
    ΤΕ
    0.64
     Jacques
    0.64
     unceasing
    0.64
     poliéster
    0.64
    Activations Density 0.057%

    No Known Activations