© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63680
    Prev
    Next
    INDEX
    Explanations

    availability, offers, flights

    np_acts-logits-general · gemini-2.5-flash-lite

    coordinates, compare, case, release, sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Staff
    0.52
    Asset
    0.51
    North
    0.51
    Vehicle
    0.51
    Creative
    0.50
    Stone
    0.49
    Celebr
    0.49
    г
    0.48
    Symbol
    0.48
    с
    0.47
    POSITIVE LOGITS
     stunted
    0.48
     firmness
    0.47
     coarsely
    0.47
     sonucu
    0.47
     puree
    0.46
    簸
    0.46
     siècles
    0.45
     takže
    0.44
     এমনকি
    0.44
     plasticity
    0.44
    Activations Density 0.001%

    No Known Activations