© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118023
    Prev
    Next
    INDEX
    Explanations

    headings and specific phrases

    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
     AVEC
    -0.94
     ESTADO
    -0.84
     about
    -0.82
    訛
    -0.81
    jeg
    -0.80
     商务
    -0.78
     sinon
    -0.77
    贋
    -0.77
    Equi
    -0.77
    odotus
    -0.77
    POSITIVE LOGITS
     trajets
    0.89
    тельностью
    0.88
    }/*
    0.83
    vetica
    0.83
    ෆ
    0.83
     doua
    0.82
     dépenses
    0.82
    푉
    0.82
     ず
    0.82
     Elemente
    0.80
    Activations Density 0.000%

    No Known Activations