© 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. 38405
    Prev
    Next
    INDEX
    Explanations

    attraction and forces

    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
    ciech
    -0.83
    ίη
    -0.82
     hộp
    -0.77
     vysok
    -0.76
    dized
    -0.76
    📀
    -0.76
     prendre
    -0.75
    umbers
    -0.75
    culature
    -0.75
     καλ
    -0.74
    POSITIVE LOGITS
     attraction
    4.19
     Attraction
    3.41
     attract
    3.30
    attraction
    3.20
     attracting
    3.20
     attracts
    3.05
     attracted
    3.02
    Attra
    2.98
     attractions
    2.95
     attractive
    2.86
    Activations Density 0.066%

    No Known Activations