© 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. 45640
    Prev
    Next
    INDEX
    Explanations

    boolean otherwise false

    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
    orElseThrow
    -0.84
    oré
    -0.83
    endrait
    -0.79
    staande
    -0.79
    找不到
    -0.78
    OrBuilder
    -0.78
     Buxton
    -0.77
    何より
    -0.77
    IORITY
    -0.76
    länge
    -0.76
    POSITIVE LOGITS
     Transitions
    0.86
     panelists
    0.81
     Plans
    0.79
     neutral
    0.75
    omonas
    0.74
    occupe
    0.73
     backpacks
    0.73
     neutre
    0.73
     straps
    0.72
    TRANS
    0.72
    Activations Density 0.001%

    No Known Activations