© 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. 64729
    Prev
    Next
    INDEX
    Explanations

    career prospects

    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
    pre
    -1.12
     Futebol
    -0.92
    vää
    -0.91
     ווי
    -0.88
    pret
    -0.87
     giai
    -0.82
     preoperative
    -0.82
    PX
    -0.82
     Reserva
    -0.82
    ENCED
    -0.81
    POSITIVE LOGITS
     externas
    1.02
     paroisse
    1.01
     animada
    1.00
     naše
    0.94
     inspirada
    0.93
     domés
    0.93
     fotográfico
    0.93
    مصادر
    0.93
     filmen
    0.90
     Désolé
    0.90
    Activations Density 0.033%

    No Known Activations