© 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. 105515
    Prev
    Next
    INDEX
    Explanations

    mathematical notation: matrices, binomials

    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
    鍗
    -1.99
     have
    -1.95
     ersten
    -1.91
     Several
    -1.75
    </b>
    -1.73
     Particularly
    -1.73
    );
    -1.71
    </h5>
    -1.70
     Adding
    -1.70
     In
    -1.69
    POSITIVE LOGITS
    al
    2.44
    of
    2.06
     ſy
    2.03
    .\
    1.94
    神
    1.84
    翃
    1.81
    廰
    1.78
    臏
    1.76
    0
    1.75
    ずに
    1.73
    Activations Density 0.002%

    No Known Activations