© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130118
    Prev
    Next
    INDEX
    Explanations

    varying permeability model

    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
     hyö
    -0.94
    </h1>
    -0.94
    Ⱦ
    -0.90
     including
    -0.89
     insumos
    -0.88
    Է
    -0.87
    二年
    -0.84
    っけ
    -0.84
     compétence
    -0.84
    ‪.‬‬
    -0.82
    POSITIVE LOGITS
    ânico
    1.04
     этих
    1.01
     supprim
    0.95
     aidé
    0.93
    emony
    0.92
     Ländern
    0.89
    isés
    0.89
     extrapolated
    0.88
    きち
    0.88
    стр
    0.86
    Activations Density 0.069%

    No Known Activations