© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 944
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     then
    -1.37
     or
    -1.17
    //!
    
    -1.09
     and
    -1.09
     тогда
    -1.04
    `),
    -1.04
     from
    -1.02
    為に
    -1.02
    )="
    -1.00
    ()),
    -1.00
    POSITIVE LOGITS
    お弁当
    1.05
    トッピング
    0.98
    也很
    0.98
    個人的には
    0.97
     asesinado
    0.94
    pecially
    0.94
    ですが
    0.94
    但也
    0.93
     поскольку
    0.91
    了你
    0.91
    Activations Density 0.028%

    No Known Activations