© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103130
    Prev
    Next
    INDEX
    Explanations

    institutions, education, and specific fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catch
    -1.67
    Catch
    -1.47
     Catch
    -1.45
    catch
    -1.40
    catching
    -1.31
    CATCH
    -1.31
     catching
    -1.30
     caught
    -1.23
     catches
    -1.23
    Catching
    -1.09
    POSITIVE LOGITS
     já
    0.81
     高等
    0.78
     diploma
    0.78
     gestorben
    0.75
     skup
    0.74
    setProperty
    0.72
    izziness
    0.72
    яви
    0.72
    πως
    0.72
    mentor
    0.71
    Activations Density 0.007%

    No Known Activations