© 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. 38548
    Prev
    Next
    INDEX
    Explanations

    code context function

    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
    йо
    -0.79
     activ
    -0.72
    Timestamp
    -0.70
     Troop
    -0.68
    kovich
    -0.68
    inter
    -0.66
    marc
    -0.66
    进制
    -0.66
    PathVariable
    -0.65
    template
    -0.65
    POSITIVE LOGITS
     bambú
    0.76
     menyiapkan
    0.69
     प्र
    0.69
    愤
    0.68
    Reprints
    0.68
    beqa
    0.68
     lesbian
    0.67
    probable
    0.67
    liothè
    0.67
     neck
    0.67
    Activations Density 0.043%

    No Known Activations