© 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. 49591
    Prev
    Next
    INDEX
    Explanations

    news content

    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
     style
    -0.74
    AttributeName
    -0.72
     спеціаль
    -0.71
    ੂੰ
    -0.71
    瞋
    -0.70
     القيام
    -0.68
     하고
    -0.68
    itz
    -0.68
     these
    -0.67
    پل
    -0.66
    POSITIVE LOGITS
    hooter
    0.78
     יוד
    0.73
    mina
    0.69
    Eds
    0.67
     aik
    0.67
     Mosa
    0.66
    orsing
    0.66
     ברו
    0.66
    isable
    0.66
    λογ
    0.66
    Activations Density 0.039%

    No Known Activations