© 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. 70076
    Prev
    Next
    INDEX
    Explanations

    Q followed by colon

    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
    -1.43
     like
    -1.36
    pullover
    -1.33
     calciatore
    -1.32
     hanggang
    -1.30
     their
    -1.27
     wij
    -1.24
     they
    -1.22
     çünkü
    -1.21
    -1.21
    POSITIVE LOGITS
     关于
    1.44
    いますが
    1.38
     produrre
    1.34
     Após
    1.30
     לאחר
    1.30
     Setelah
    1.30
    ヨーロ
    1.30
     maioria
    1.28
    Presentación
    1.27
    摒
    1.27
    Activations Density 0.000%

    No Known Activations