© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90720
    Prev
    Next
    INDEX
    Explanations

    NM 225

    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
     imprensa
    -0.96
    lový
    -0.93
     Gestión
    -0.93
     indústria
    -0.88
    acles
    -0.88
     Temporada
    -0.88
    lierung
    -0.87
     Agustus
    -0.87
    никах
    -0.83
    ètres
    -0.82
    POSITIVE LOGITS
     eccell
    1.19
    Kval
    1.13
    ardı
    1.09
    Seni
    1.03
     specifiche
    0.99
    Indien
    0.98
    Vä
    0.96
     triko
    0.95
    Tento
    0.95
     esigenze
    0.93
    Activations Density 0.000%

    No Known Activations