© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107175
    Prev
    Next
    INDEX
    Explanations

    dream act and immigration

    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
    鸡蛋
    -0.82
    俪
    -0.76
    meno
    -0.76
     barcel
    -0.74
     avengers
    -0.73
     Handicap
    -0.73
    yors
    -0.73
    carousel
    -0.72
     tarta
    -0.72
     cono
    -0.71
    POSITIVE LOGITS
     Dream
    1.85
     DREAM
    1.68
    Dream
    1.48
     dream
    1.45
     Dreamer
    1.41
    dream
    1.37
     dreamer
    1.36
    DREAM
    1.36
     dreams
    1.13
     Dreams
    1.11
    Activations Density 0.031%

    No Known Activations