© 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. 114317
    Prev
    Next
    INDEX
    Explanations

    locations and specific terms

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

    handling unknown or rare words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     "");
    0.54
    cpf
    0.50
    henden
    0.49
     "")
    0.49
     даних
    0.46
    ructor
    0.46
    𝗱
    0.46
    étrico
    0.45
     '-')
    0.44
     তৃণমূল
    0.44
    POSITIVE LOGITS
    s
    0.54
    kker
    0.51
     marinas
    0.50
     Prefecture
    0.48
     മിക
    0.44
     especific
    0.44
    kke
    0.43
    س
    0.43
     capacidad
    0.43
     airports
    0.43
    Activations Density 0.000%

    No Known Activations