© 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. 109601
    Prev
    Next
    INDEX
    Explanations

    numbers to words

    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
     sounds
    -0.68
    sounds
    -0.65
     déb
    -0.65
    setLayoutParams
    -0.65
     API
    -0.65
    wagon
    -0.65
    meh
    -0.64
    芾
    -0.63
    pling
    -0.63
     Positive
    -0.63
    POSITIVE LOGITS
     Văn
    0.65
    ثر
    0.65
    пу
    0.65
     խ
    0.61
    umented
    0.61
     Ivanov
    0.60
    NOTE
    0.60
     Europe
    0.60
     thái
    0.59
    NSObject
    0.59
    Activations Density 0.080%

    No Known Activations