© 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. 76425
    Prev
    Next
    INDEX
    Explanations

    onCreate method signatures with Bundle

    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
     Δι
    -0.88
    Ши
    -0.83
    pazität
    -0.81
     Tiere
    -0.81
    ISTE
    -0.79
     negation
    -0.77
    นะนำ
    -0.76
    anillo
    -0.75
     Scotia
    -0.74
    Dichlorobenzene
    -0.74
    POSITIVE LOGITS
     berkom
    0.79
     TAMBÉM
    0.77
    phage
    0.76
     го
    0.75
     хотя
    0.75
    であり
    0.75
    ええ
    0.73
    mV
    0.71
     pozna
    0.71
    ーツ
    0.71
    Activations Density 0.006%

    No Known Activations