© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1162
    Prev
    Next
    INDEX
    Explanations

    as a definition

    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
     with
    -2.11
     on
    -1.92
     in
    -1.66
     but
    -1.64
     они
    -1.56
     both
    -1.53
     összefoglal
    -1.52
     according
    -1.49
    Sometimes
    -1.45
     This
    -1.43
    POSITIVE LOGITS
    </h3>
    2.05
    "]();
    1.81
     likely
    1.71
    敺
    1.55
     
    1.50
    咵
    1.49
    </h2>
    1.48
    ズキ
    1.46
     ."
    1.46
     movimento
    1.46
    Activations Density 0.018%

    No Known Activations