© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 107344
    Prev
    Next
    INDEX
    Explanations

    salsa and salsa fresca

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Content
    0.64
    Order
    0.63
    ._
    0.62
    Metrics
    0.62
    From
    0.61
    Id
    0.61
    Data
    0.61
    Lock
    0.59
    }
    0.59
    Color
    0.58
    POSITIVE LOGITS
     powied
    0.63
     diambil
    0.56
     escolh
    0.54
     giusto
    0.54
     conlle
    0.54
    দারের
    0.53
     fornisce
    0.52
     faible
    0.52
     perbedaan
    0.52
     neke
    0.51
    Activations Density 0.001%

    No Known Activations