© 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. 60416
    Prev
    Next
    INDEX
    Explanations

    size, length, or duration descriptions

    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
    鉭
    -0.98
    levels
    -0.96
     LEVELS
    -0.91
    atures
    -0.88
    width
    -0.82
    weisung
    -0.82
     tristesse
    -0.81
    を読んで
    -0.81
    npc
    -0.80
    Taille
    -0.80
    POSITIVE LOGITS
     οποία
    0.89
    Unexpected
    0.87
    éroport
    0.82
    넵
    0.81
    bona
    0.79
     raras
    0.79
     Unexpected
    0.78
     hulle
    0.78
    vast
    0.77
    。"
    0.77
    Activations Density 0.245%

    No Known Activations