© 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. 124584
    Prev
    Next
    INDEX
    Explanations

    gaming terms and mechanics

    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
     CREAT
    -1.36
     入荷
    -1.30
    inkled
    -1.28
    儸
    -1.27
     incluida
    -1.26
    aneers
    -1.23
     simplif
    -1.22
     ALREADY
    -1.22
    simplified
    -1.20
     CREATED
    -1.20
    POSITIVE LOGITS
    er
    1.22
    -.
    1.17
     stumbled
    1.17
    》
    1.16
     like
    1.14
     siker
    1.13
     at
    1.13
     with
    1.11
     steered
    1.10
    </h4>
    1.09
    Activations Density 0.020%

    No Known Activations