© 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. 22-GEMMASCOPE-RES-131K
    7. 73391
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or definitions

    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
     cannes
    -0.90
     别墅
    -0.89
     MASK
    -0.86
    bisoft
    -0.85
     newData
    -0.82
     mobilier
    -0.82
     toilette
    -0.81
    ＇
    -0.81
    konos
    -0.81
     shouldBe
    -0.80
    POSITIVE LOGITS
     puisque
    1.31
     puisqu
    1.22
    Indeed
    1.02
    судар
    1.02
     since
    1.02
    utnant
    0.96
     hasn
    0.96
    Example
    0.96
    Certainly
    0.94
    etti
    0.94
    Activations Density 0.046%

    No Known Activations