© 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. 47958
    Prev
    Next
    INDEX
    Explanations

    license and copyright

    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
    olstein
    -0.70
    bilirsiniz
    -0.69
     חס
    -0.68
     YS
    -0.68
    łów
    -0.66
     implantation
    -0.66
    Vent
    -0.65
     attached
    -0.65
     парт
    -0.65
    gjenge
    -0.64
    POSITIVE LOGITS
    Allocator
    0.71
    prises
    0.69
    quakes
    0.69
    وامل
    0.68
    erton
    0.67
    δε
    0.67
     Ál
    0.66
    avoir
    0.66
     giveaway
    0.66
     Choice
    0.65
    Activations Density 0.067%

    No Known Activations