© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73191
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and problems

    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_22/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
     complicado
    -1.00
    mologie
    -0.94
    oció
    -0.93
     tomate
    -0.93
    beiter
    -0.92
     Papier
    -0.91
    </blockquote>
    -0.90
     imó
    -0.90
     impracticable
    -0.88
    zada
    -0.87
    POSITIVE LOGITS
    𝔄
    0.92
     then
    0.90
     vecchia
    0.90
    bgcolor
    0.88
    ctuations
    0.87
     dậy
    0.87
     macchina
    0.86
    Kemudian
    0.86
     moglie
    0.85
     compagnia
    0.84
    Activations Density 0.019%

    No Known Activations