© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    doing easier

    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
     bonos
    -0.90
     adaptés
    -0.75
     aplikasi
    -0.75
     descuentos
    -0.73
     delantero
    -0.73
    मर
    -0.72
    itism
    -0.71
     desconto
    -0.71
     muñeca
    -0.71
     Steuerung
    -0.70
    POSITIVE LOGITS
     ease
    2.20
     Ease
    2.02
    Ease
    1.73
    ease
    1.56
     Doing
    1.55
     business
    1.46
    Doing
    1.44
     doing
    1.38
     easier
    1.34
    doing
    1.27
    Activations Density 0.010%

    No Known Activations