© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7637
    Prev
    Next
    INDEX
    Explanations

    items in lists

    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
     dobry
    -1.43
     it
    -1.31
    になれば
    -1.30
     that
    -1.30
     "]";
    -1.27
     jurídica
    -1.27
    
    -1.25
     zwier
    -1.23
     szcz
    -1.23
     zwi
    -1.21
    POSITIVE LOGITS
     with
    1.67
     and
    1.50
     dengan
    1.44
    相同
    1.31
    任意
    1.31
    两个
    1.27
    OOTDTY
    1.24
     tenerife
    1.23
    是非常
    1.23
     from
    1.20
    Activations Density 0.204%

    No Known Activations