© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8537
    Prev
    Next
    INDEX
    Explanations

    high profile

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

    high profile

    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_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     resiliency
    0.45
     ohm
    0.42
     resil
    0.41
     DOR
    0.41
     efficiencies
    0.41
    Dor
    0.41
     performing
    0.40
     Performing
    0.39
     (>
    0.39
     bền
    0.39
    POSITIVE LOGITS
     profile
    0.81
    profile
    0.81
     प्रोफाइल
    0.79
     perfil
    0.70
     profil
    0.68
     Profile
    0.67
    Profile
    0.63
     flown
    0.63
    ranking
    0.62
    profil
    0.62
    Activations Density 0.034%

    No Known Activations