© 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. 48313
    Prev
    Next
    INDEX
    Explanations

    meaning immersion and dispersion

    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
     μο
    -0.91
    없
    -0.87
    そう
    -0.84
     smtp
    -0.84
     применения
    -0.83
     Airborne
    -0.81
     tph
    -0.79
    レ
    -0.77
     itemName
    -0.76
     Bekasi
    -0.76
    POSITIVE LOGITS
     immersion
    1.49
    Immer
    1.41
     Immer
    1.40
     immersive
    1.24
     immer
    1.22
    immer
    1.19
     погру
    1.13
    sive
    1.12
     Immersion
    1.09
     immerse
    1.07
    Activations Density 0.022%

    No Known Activations