© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40335
    Prev
    Next
    INDEX
    Explanations

    qualifying negation after best

    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
     AUSSI
    -1.63
     opini
    -1.59
    ———-
    -1.56
     cubo
    -1.55
     BIBLIO
    -1.55
     analisis
    -1.52
     lini
    -1.52
     adem
    -1.51
     nila
    -1.49
    嵎
    -1.48
    POSITIVE LOGITS
    7
    2.25
    8
    2.23
    1
    2.13
    4
    2.06
    6
    1.98
    0
    1.94
    5
    1.89
    3
    1.88
    9
    1.73
    2
    1.70
    Activations Density 0.005%

    No Known Activations