© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17856
    Prev
    Next
    INDEX
    Explanations

    dreams and wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prawdzi
    0.38
    来店
    0.35
    亳
    0.35
    နေရာ
    0.33
    滋
    0.33
    ುತ್ತಾರೆ
    0.33
    Innov
    0.33
     balk
    0.32
    ్యూ
    0.32
    匿
    0.32
    POSITIVE LOGITS
     wish
    1.56
    wish
    1.41
     Wish
    1.37
     wishes
    1.33
    Wish
    1.32
     wishlist
    1.16
     Wishes
    1.14
     dream
    1.13
     dreams
    1.13
     dreaming
    1.09
    Activations Density 0.115%

    No Known Activations