© 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. 10-GEMMASCOPE-RES-131K
    7. 75631
    Prev
    Next
    INDEX
    Explanations

    LaTeX environments and arguments

    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_10/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
     in
    -2.03
     but
    -1.53
    をご覧ください
    -1.48
     without
    -1.40
     \$
    -1.36
     through
    -1.35
    ⟐
    -1.33
     viejas
    -1.30
    towych
    -1.28
    不被
    -1.28
    POSITIVE LOGITS
     específica
    1.92
     empêcher
    1.92
     Frequently
    1.81
    .
    1.80
    ândia
    1.78
    _
    1.78
     sintió
    1.77
    媄
    1.77
    ]
    1.77
     unimaginable
    1.76
    Activations Density 0.003%

    No Known Activations