© 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. 67513
    Prev
    Next
    INDEX
    Explanations

    die/Dis/the article

    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
     him
    -2.36
     bepaalde
    -2.34
     związ
    -2.17
     dotyczą
    -2.16
     genauer
    -2.14
     the
    -2.13
    幸好
    -2.11
     anderer
    -2.09
    じゃなくて
    -2.08
     descrito
    -2.05
    POSITIVE LOGITS
    i
    2.64
    缫
    2.38
    }
    2.28
    jenige
    2.23
     этим
    2.20
     них
    2.19
     ganze
    2.08
     polisi
    2.05
    d
    2.03
    řízen
    1.99
    Activations Density 0.001%

    No Known Activations