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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59547
    Prev
    Next
    INDEX
    Explanations

    catch, TODO, create, Caucasian, Also, Successful, Significance

    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
     faded
    -0.81
    ⃝
    -0.79
    VERIFY
    -0.79
    preloader
    -0.75
    ッパ
    -0.73
     frische
    -0.73
     his
    -0.73
     符号
    -0.72
    гих
    -0.72
     japonés
    -0.71
    POSITIVE LOGITS
     catch
    1.14
     Catch
    1.04
    catcher
    1.00
    catch
    0.98
    Catch
    0.94
     Auto
    0.91
     caught
    0.90
    printStackTrace
    0.90
    Auto
    0.90
     catches
    0.90
    Activations Density 0.001%

    No Known Activations