© 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. 119902
    Prev
    Next
    INDEX
    Explanations

    astronomical bodies or technical terms

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

    mRNA technology

    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
     poziomie
    0.57
    럇
    0.52
     रिज
    0.51
    AssignableFrom
    0.48
     уровне
    0.48
    acyjne
    0.47
    HeightSizeMode
    0.47
    hattis
    0.46
     odpowiedzi
    0.45
    ফেট
    0.45
    POSITIVE LOGITS
     N
    0.51
     Donna
    0.48
     Bay
    0.46
    ">
    0.46
     Bayer
    0.45
     Dass
    0.45
    "
    0.44
     Three
    0.44
     El
    0.43
    E
    0.43
    Activations Density 0.000%

    No Known Activations