© 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. 41769
    Prev
    Next
    INDEX
    Explanations

    and followed by action verbs

    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
     qualsiasi
    -1.76
     ayudará
    -1.66
     vuestro
    -1.52
     obtend
    -1.49
     oferece
    -1.47
     frecuentemente
    -1.46
     Añade
    -1.45
     vuestra
    -1.45
    appartement
    -1.43
     molti
    -1.42
    POSITIVE LOGITS
     and
    1.98
     ‘
    1.43
    šní
    1.41
    }
    1.39
    ’
    1.38
    geen
    1.34
    一样
    1.29
    Склад
    1.29
     igen
    1.27
     amerik
    1.27
    Activations Density 0.047%

    No Known Activations