© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115675
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming references

    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
    irte
    -0.78
    ohist
    -0.75
     maximization
    -0.74
    uluk
    -0.72
     дети
    -0.69
    Chau
    -0.68
    Sino
    -0.68
    phins
    -0.68
     DOWN
    -0.68
    Decor
    -0.67
    POSITIVE LOGITS
    utí
    0.74
    setTransform
    0.67
    room
    0.63
    									
    0.62
    KM
    0.62
     serwis
    0.59
    充足
    0.59
     συ
    0.59
    デザイナー
    0.59
    話の
    0.58
    Activations Density 0.098%

    No Known Activations