© 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. 48429
    Prev
    Next
    INDEX
    Explanations

    always wanted to dream

    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
     BaseActivity
    -0.81
     Hæ
    -0.81
    imee
    -0.79
    ânica
    -0.76
    ánica
    -0.75
    不喜欢
    -0.75
    PMailer
    -0.74
    fiche
    -0.74
     benevol
    -0.73
     engag
    -0.73
    POSITIVE LOGITS
     dream
    5.34
     dreams
    4.78
     dreaming
    4.41
     dreamed
    4.28
    dream
    4.00
     DREAM
    3.88
     dreamt
    3.80
    dreams
    3.53
    Dream
    3.36
     Dreams
    3.34
    Activations Density 0.084%

    No Known Activations