© 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. 23722
    Prev
    Next
    INDEX
    Explanations

    experimental observations

    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
    μένου
    -0.76
    RequestMapping
    -0.74
    δας
    -0.73
     hidratante
    -0.72
     Scu
    -0.72
    vian
    -0.71
    truck
    -0.71
    люс
    -0.70
     الشم
    -0.69
    öfe
    -0.69
    POSITIVE LOGITS
     experimental
    5.41
     experimentally
    4.56
    experimental
    4.34
    Experimental
    4.19
     Experimental
    4.09
     эксперимента
    3.52
    EXPERIMENTAL
    3.34
     empirical
    3.28
     EXPERIMENTAL
    3.17
    实验
    3.14
    Activations Density 0.233%

    No Known Activations