© 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. 108029
    Prev
    Next
    INDEX
    Explanations

    Contribution, Kaitaia, Q:, Schönburg, /

    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
     even
    -0.94
     même
    -0.87
    entification
    -0.85
    )?
    -0.85
    unto
    -0.83
    ответ
    -0.83
    latimes
    -0.82
    苑
    -0.82
     мм
    -0.80
     träd
    -0.80
    POSITIVE LOGITS
    iksa
    0.89
    是怎么回事
    0.89
     arric
    0.85
    🧒
    0.84
    ofern
    0.83
    forderungen
    0.83
    𝖨
    0.82
    色んな
    0.82
     [/
    0.82
    anmoins
    0.81
    Activations Density 0.004%

    No Known Activations