© 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. 48255
    Prev
    Next
    INDEX
    Explanations

    reasons why

    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
    }
    -1.78
    媪
    -1.60
    Уже
    -1.59
     profondeur
    -1.58
    dáms
    -1.57
     tył
    -1.53
    ,”
    -1.52
    德國
    -1.51
    這次
    -1.48
     impor
    -1.47
    POSITIVE LOGITS
     you
    1.98
    {
    1.84
    L
    1.72
    一抹
    1.66
    </h2>
    1.63
     gbc
    1.55
    itamente
    1.55
     şi
    1.53
    it
    1.53
     DON
    1.52
    Activations Density 0.005%

    No Known Activations