© 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. 84380
    Prev
    Next
    INDEX
    Explanations

    .rb: after rb

    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
     who
    -0.91
     anything
    -0.85
    Тогда
    -0.82
    emény
    -0.82
    婪
    -0.81
     APS
    -0.78
    getNumberOf
    -0.77
    setField
    -0.77
     sớm
    -0.76
    直播间
    -0.76
    POSITIVE LOGITS
     pressione
    0.88
     próprio
    0.85
     تكون
    0.83
     tekanan
    0.83
     presión
    0.82
     figliu
    0.82
     stesso
    0.81
     hilar
    0.81
    läufig
    0.79
    inição
    0.79
    Activations Density 0.001%

    No Known Activations